Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 370 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.7130. Min Act: -0.1700
Data Index: 5853158 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.6974. Min Act: -0.1700
Data Index: 7152002 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.6505. Min Act: -0.1700
Data Index: 3523893 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.6035. Min Act: -0.1700
Data Index: 281638 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.6035. Min Act: -0.1700
Data Index: 2649469 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5879. Min Act: -0.1700
Data Index: 3991017 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5879. Min Act: -0.1700
Data Index: 4513235 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5722. Min Act: -0.1700
Data Index: 3408907 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5566. Min Act: -0.1700
Data Index: 6856082 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5566. Min Act: -0.1700
Data Index: 4782120 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5409. Min Act: -0.1700
Data Index: 6982479 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5252. Min Act: -0.1700
Data Index: 1295511 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5252. Min Act: -0.1700
Data Index: 4843278 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5252. Min Act: -0.1700
Data Index: 3755825 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5252. Min Act: -0.1700
Data Index: 8308838 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5252. Min Act: -0.1700
Data Index: 326363 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5096. Min Act: -0.1700
Data Index: 5379140 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.4939. Min Act: -0.1700
Data Index: 6530376 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5096. Min Act: -0.1700
Data Index: 6017869 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7130. Min Range: -3.7130
Max Act: 3.5096. Min Act: -0.1700
Data Index: 50856 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19