Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3302 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3353. Min Range: -7.3353
Max Act: 7.3353. Min Act: -0.1700
Data Index: 7787057 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3353. Min Range: -7.3353
Max Act: 7.3041. Min Act: -0.1700
Data Index: 3955845 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3353. Min Range: -7.3353
Max Act: 7.0541. Min Act: -0.1700
Data Index: 1071429 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3353. Min Range: -7.3353
Max Act: 7.0228. Min Act: -0.1700
Data Index: 1863312 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.9916. Min Act: -0.1700
Data Index: 8825147 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.9603. Min Act: -0.1700
Data Index: 3693709 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.9291. Min Act: -0.1700
Data Index: 2552039 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.9603. Min Act: -0.1700
Data Index: 868296 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.9291. Min Act: -0.1700
Data Index: 4647595 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.8978. Min Act: -0.1700
Data Index: 6043972 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.8666. Min Act: -0.1700
Data Index: 841735 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.8353. Min Act: -0.1700
Data Index: 4416817 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.8041. Min Act: -0.1700
Data Index: 4878382 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.8041. Min Act: -0.1700
Data Index: 2332361 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.8041. Min Act: -0.1700
Data Index: 6279555 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.7728. Min Act: -0.1700
Data Index: 977413 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.7728. Min Act: -0.1700
Data Index: 4346048 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.7416. Min Act: -0.1700
Data Index: 4835143 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.7416. Min Act: -0.1700
Data Index: 1964118 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3353. Min Range: -7.3353
Max Act: 6.7416. Min Act: -0.1700
Data Index: 4748814 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19