Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2212 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.9906. Min Act: -0.1700
Data Index: 4923230 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.5531. Min Act: -0.1700
Data Index: 2437668 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.5531. Min Act: -0.1700
Data Index: 3933197 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.6156. Min Act: -0.1700
Data Index: 5848135 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.3969. Min Act: -0.1700
Data Index: 5211233 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.2719. Min Act: -0.1700
Data Index: 5209724 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.3031. Min Act: -0.1700
Data Index: 2238490 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.2719. Min Act: -0.1700
Data Index: 1025136 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.2719. Min Act: -0.1700
Data Index: 2967584 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.2406. Min Act: -0.1700
Data Index: 7418391 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.2094. Min Act: -0.1700
Data Index: 203318 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.2719. Min Act: -0.1700
Data Index: 4309714 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.2094. Min Act: -0.1700
Data Index: 6790090 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.2094. Min Act: -0.1700
Data Index: 7912539 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.1469. Min Act: -0.1700
Data Index: 3213312 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.1781. Min Act: -0.1700
Data Index: 8086657 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.1781. Min Act: -0.1700
Data Index: 5592631 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.1469. Min Act: -0.1700
Data Index: 950699 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.1469. Min Act: -0.1700
Data Index: 2455373 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9906. Min Range: -5.9906
Max Act: 5.1469. Min Act: -0.1700
Data Index: 1987781 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19