Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 544 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5530. Min Range: -6.5530
Max Act: 6.5530. Min Act: -0.1700
Data Index: 7216859 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5530. Min Range: -6.5530
Max Act: 6.4905. Min Act: -0.1700
Data Index: 1115523 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5530. Min Range: -6.5530
Max Act: 6.2093. Min Act: -0.1700
Data Index: 1864476 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5530. Min Range: -6.5530
Max Act: 6.1780. Min Act: -0.1700
Data Index: 8546180 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5530. Min Range: -6.5530
Max Act: 6.1155. Min Act: -0.1700
Data Index: 2647263 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5530. Min Range: -6.5530
Max Act: 6.1155. Min Act: -0.1700
Data Index: 2455889 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5530. Min Range: -6.5530
Max Act: 6.0530. Min Act: -0.1700
Data Index: 8774553 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5530. Min Range: -6.5530
Max Act: 6.0218. Min Act: -0.1700
Data Index: 1467084 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.9905. Min Act: -0.1700
Data Index: 2565892 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.9593. Min Act: -0.1700
Data Index: 3968628 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.9280. Min Act: -0.1700
Data Index: 7102281 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.8968. Min Act: -0.1700
Data Index: 7286480 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.8968. Min Act: -0.1700
Data Index: 4948346 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.8968. Min Act: -0.1700
Data Index: 8741837 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.8343. Min Act: -0.1700
Data Index: 4144939 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.8655. Min Act: -0.1700
Data Index: 7138497 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.8655. Min Act: -0.1700
Data Index: 6158786 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.8655. Min Act: -0.1700
Data Index: 6350682 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.8343. Min Act: -0.1700
Data Index: 1010054 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5530. Min Range: -6.5530
Max Act: 5.8030. Min Act: -0.1700
Data Index: 8453281 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19