Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2797 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3964. Min Range: -8.3964
Max Act: 8.3964. Min Act: -0.1700
Data Index: 5106147 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3964. Min Range: -8.3964
Max Act: 8.0839. Min Act: -0.1700
Data Index: 4181846 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3964. Min Range: -8.3964
Max Act: 8.1464. Min Act: -0.1700
Data Index: 308811 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3964. Min Range: -8.3964
Max Act: 8.0214. Min Act: -0.1700
Data Index: 3786801 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3964. Min Range: -8.3964
Max Act: 8.0214. Min Act: -0.1700
Data Index: 1802851 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.9589. Min Act: -0.1671
Data Index: 3249698 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.9589. Min Act: -0.1700
Data Index: 8468117 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.9589. Min Act: -0.1700
Data Index: 5355955 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.8651. Min Act: -0.1700
Data Index: 3541445 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.8339. Min Act: -0.1700
Data Index: 879510 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.8026. Min Act: -0.1700
Data Index: 3935380 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.7714. Min Act: -0.1700
Data Index: 5117793 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.7714. Min Act: -0.1700
Data Index: 4093976 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.6776. Min Act: -0.1696
Data Index: 4594236 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.7089. Min Act: -0.1700
Data Index: 4949559 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.7089. Min Act: -0.1699
Data Index: 2130073 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.6776. Min Act: -0.1700
Data Index: 371120 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.6776. Min Act: -0.1700
Data Index: 2196608 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.7089. Min Act: -0.1700
Data Index: 6559799 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3964. Min Range: -8.3964
Max Act: 7.6464. Min Act: -0.1700
Data Index: 3165350 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19