Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4780. Min Range: -9.4780
Max Act: 9.4780. Min Act: -0.1700
Data Index: 5973891 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4780. Min Range: -9.4780
Max Act: 9.1030. Min Act: -0.1700
Data Index: 3873196 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4780. Min Range: -9.4780
Max Act: 9.1030. Min Act: -0.1700
Data Index: 3547251 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4780. Min Range: -9.4780
Max Act: 9.1030. Min Act: -0.1700
Data Index: 5276512 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4780. Min Range: -9.4780
Max Act: 9.0405. Min Act: -0.1700
Data Index: 8650194 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.9780. Min Act: -0.1700
Data Index: 7349102 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.9780. Min Act: -0.1700
Data Index: 854190 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.9780. Min Act: -0.1700
Data Index: 8371914 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.8530. Min Act: -0.1700
Data Index: 5574804 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.8530. Min Act: -0.1700
Data Index: 4616321 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.7280. Min Act: -0.1700
Data Index: 4638861 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.7280. Min Act: -0.1700
Data Index: 7913536 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.7280. Min Act: -0.1700
Data Index: 1270845 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.7280. Min Act: -0.1700
Data Index: 6510732 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.6655. Min Act: -0.1700
Data Index: 1979813 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.6030. Min Act: -0.1700
Data Index: 5154058 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.5405. Min Act: -0.1700
Data Index: 4004355 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.6030. Min Act: -0.1700
Data Index: 5078150 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.6030. Min Act: -0.1700
Data Index: 8472360 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4780. Min Range: -9.4780
Max Act: 8.5405. Min Act: -0.1700
Data Index: 6185695 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19