Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2070 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.8142. Min Act: -0.1700
Data Index: 4672598 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.5329. Min Act: -0.1700
Data Index: 6099877 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.4392. Min Act: -0.1700
Data Index: 6519138 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.4079. Min Act: -0.1700
Data Index: 3812482 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.3454. Min Act: -0.1700
Data Index: 6366457 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.3454. Min Act: -0.1700
Data Index: 2927630 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.3454. Min Act: -0.1700
Data Index: 5063839 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.3454. Min Act: -0.1700
Data Index: 4679778 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.3141. Min Act: -0.1700
Data Index: 1970334 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.3141. Min Act: -0.1700
Data Index: 660257 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.2516. Min Act: -0.1700
Data Index: 6476583 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.2829. Min Act: -0.1700
Data Index: 8620888 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.2829. Min Act: -0.1700
Data Index: 6667795 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.2516. Min Act: -0.1700
Data Index: 6164859 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.2516. Min Act: -0.1700
Data Index: 6030037 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.2516. Min Act: -0.1700
Data Index: 2502076 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.2204. Min Act: -0.1700
Data Index: 7592373 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.2516. Min Act: -0.1700
Data Index: 5813489 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.2204. Min Act: -0.1700
Data Index: 4247511 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8142. Min Range: -4.8142
Max Act: 4.1891. Min Act: -0.1700
Data Index: 5811525 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19