Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 907 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.7233. Min Act: -0.1700
Data Index: 4768717 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.7073. Min Act: -0.1700
Data Index: 3859837 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.6111. Min Act: -0.1700
Data Index: 2622513 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.6272. Min Act: -0.1700
Data Index: 2420734 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.5950. Min Act: -0.1700
Data Index: 6238638 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.5628. Min Act: -0.1700
Data Index: 7116512 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.5628. Min Act: -0.1700
Data Index: 8200713 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.5305. Min Act: -0.1700
Data Index: 4816746 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.5143. Min Act: -0.1700
Data Index: 1173632 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.5305. Min Act: -0.1700
Data Index: 222462 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.5143. Min Act: -0.1700
Data Index: 4185466 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.4981. Min Act: -0.1700
Data Index: 4631464 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.5305. Min Act: -0.1700
Data Index: 7872785 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.4981. Min Act: -0.1700
Data Index: 792234 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.5305. Min Act: -0.1700
Data Index: 1606695 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.4981. Min Act: -0.1700
Data Index: 598297 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.4981. Min Act: -0.1700
Data Index: 7517140 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.4981. Min Act: -0.1700
Data Index: 7964041 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.4656. Min Act: -0.1700
Data Index: 1760210 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7233. Min Range: -2.7233
Max Act: 2.4656. Min Act: -0.1700
Data Index: 948439 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19