Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2117 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.7662. Min Range: -12.7662
Max Act: 12.7662. Min Act: -0.1700
Data Index: 7381616 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7662. Min Range: -12.7662
Max Act: 12.0162. Min Act: -0.1700
Data Index: 2181906 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7662. Min Range: -12.7662
Max Act: 11.7037. Min Act: -0.1700
Data Index: 6910264 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7662. Min Range: -12.7662
Max Act: 11.7037. Min Act: -0.1700
Data Index: 4284499 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7662. Min Range: -12.7662
Max Act: 11.3287. Min Act: -0.1700
Data Index: 5690488 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7662. Min Range: -12.7662
Max Act: 11.2662. Min Act: -0.1700
Data Index: 5158852 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7662. Min Range: -12.7662
Max Act: 11.2662. Min Act: -0.1700
Data Index: 2318496 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7662. Min Range: -12.7662
Max Act: 11.0787. Min Act: -0.1700
Data Index: 3283492 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7662. Min Range: -12.7662
Max Act: 11.1412. Min Act: -0.1700
Data Index: 1216292 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7662. Min Range: -12.7662
Max Act: 11.0787. Min Act: -0.1700
Data Index: 8765065 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7662. Min Range: -12.7662
Max Act: 11.0787. Min Act: -0.1700
Data Index: 8807991 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7662. Min Range: -12.7662
Max Act: 10.9537. Min Act: -0.1700
Data Index: 572944 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7662. Min Range: -12.7662
Max Act: 11.0787. Min Act: -0.1700
Data Index: 5158847 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7662. Min Range: -12.7662
Max Act: 10.9537. Min Act: -0.1700
Data Index: 3327571 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7662. Min Range: -12.7662
Max Act: 10.9537. Min Act: -0.1700
Data Index: 2733865 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7662. Min Range: -12.7662
Max Act: 10.8287. Min Act: -0.1700
Data Index: 249276 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7662. Min Range: -12.7662
Max Act: 10.8912. Min Act: -0.1700
Data Index: 1509510 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7662. Min Range: -12.7662
Max Act: 10.7037. Min Act: -0.1700
Data Index: 2159700 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7662. Min Range: -12.7662
Max Act: 10.7037. Min Act: -0.1700
Data Index: 4944715 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7662. Min Range: -12.7662
Max Act: 10.7662. Min Act: -0.1700
Data Index: 2555244 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19