Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1007 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3582. Min Range: -7.3582
Max Act: 7.3582. Min Act: -0.1700
Data Index: 7534915 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3582. Min Range: -7.3582
Max Act: 7.2019. Min Act: -0.1700
Data Index: 7810459 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3582. Min Range: -7.3582
Max Act: 7.2019. Min Act: -0.1700
Data Index: 2198335 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3582. Min Range: -7.3582
Max Act: 7.1082. Min Act: -0.1700
Data Index: 3202347 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3582. Min Range: -7.3582
Max Act: 7.0144. Min Act: -0.1700
Data Index: 6937307 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3582. Min Range: -7.3582
Max Act: 7.0457. Min Act: -0.1700
Data Index: 3540652 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3582. Min Range: -7.3582
Max Act: 7.0144. Min Act: -0.1700
Data Index: 4262837 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.9832. Min Act: -0.1700
Data Index: 1721363 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3582. Min Range: -7.3582
Max Act: 7.0144. Min Act: -0.1699
Data Index: 434260 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.9519. Min Act: -0.1700
Data Index: 6570788 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.9832. Min Act: -0.1700
Data Index: 3079306 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.9832. Min Act: -0.1700
Data Index: 1517488 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.9832. Min Act: -0.1700
Data Index: 6437784 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.9519. Min Act: -0.1700
Data Index: 3267842 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.9207. Min Act: -0.1700
Data Index: 1622064 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.8894. Min Act: -0.1700
Data Index: 3079305 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.8894. Min Act: -0.1700
Data Index: 6039155 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.8894. Min Act: -0.1700
Data Index: 3411392 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.8894. Min Act: -0.1700
Data Index: 5139865 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3582. Min Range: -7.3582
Max Act: 6.8582. Min Act: -0.1700
Data Index: 1529380 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19