Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3202 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2316. Min Range: -6.2316
Max Act: 6.2316. Min Act: -0.1700
Data Index: 6672108 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2316. Min Range: -6.2316
Max Act: 6.0441. Min Act: -0.1700
Data Index: 5700985 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.9816. Min Act: -0.1700
Data Index: 5624581 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.9816. Min Act: -0.1700
Data Index: 3239384 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.8253. Min Act: -0.1700
Data Index: 7673742 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.8566. Min Act: -0.1700
Data Index: 3209768 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.7941. Min Act: -0.1700
Data Index: 4960497 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.7941. Min Act: -0.1700
Data Index: 1027881 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.7628. Min Act: -0.1700
Data Index: 5951975 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.7628. Min Act: -0.1700
Data Index: 3125564 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.6691. Min Act: -0.1700
Data Index: 1577416 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.6691. Min Act: -0.1700
Data Index: 2849129 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.7003. Min Act: -0.1700
Data Index: 4952485 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.6691. Min Act: -0.1700
Data Index: 8666105 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.6378. Min Act: -0.1700
Data Index: 4739355 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.6691. Min Act: -0.1700
Data Index: 3938141 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.5753. Min Act: -0.1700
Data Index: 4661010 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.6066. Min Act: -0.1700
Data Index: 8114344 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.6066. Min Act: -0.1700
Data Index: 7431768 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2316. Min Range: -6.2316
Max Act: 5.5753. Min Act: -0.1700
Data Index: 424124 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19