Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.7142. Min Act: -0.1700
Data Index: 2168366 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.6830. Min Act: -0.1700
Data Index: 3973865 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.6830. Min Act: -0.1700
Data Index: 4072080 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.6205. Min Act: -0.1700
Data Index: 5225861 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.5892. Min Act: -0.1700
Data Index: 6402545 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.6205. Min Act: -0.1700
Data Index: 7660882 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.5580. Min Act: -0.1700
Data Index: 390361 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.5580. Min Act: -0.1700
Data Index: 7645019 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.5580. Min Act: -0.1700
Data Index: 5355059 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.5580. Min Act: -0.1700
Data Index: 6079047 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.5580. Min Act: -0.1700
Data Index: 4613586 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.5892. Min Act: -0.1700
Data Index: 5623970 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.4955. Min Act: -0.1700
Data Index: 7620082 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.5580. Min Act: -0.1700
Data Index: 5367329 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.4955. Min Act: -0.1700
Data Index: 6076651 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.4955. Min Act: -0.1700
Data Index: 4176898 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.4642. Min Act: -0.1700
Data Index: 1886786 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.4955. Min Act: -0.1700
Data Index: 5924981 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.4642. Min Act: -0.1700
Data Index: 7438783 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7142. Min Range: -5.7142
Max Act: 5.4955. Min Act: -0.1700
Data Index: 3350900 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19