Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.3885. Min Act: -0.1700
Data Index: 1107174 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.3571. Min Act: -0.1700
Data Index: 1288278 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.3571. Min Act: -0.1700
Data Index: 7983349 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.3257. Min Act: -0.1700
Data Index: 3593280 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.3257. Min Act: -0.1700
Data Index: 8553738 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.3257. Min Act: -0.1700
Data Index: 8252381 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.3257. Min Act: -0.1700
Data Index: 8197476 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.3257. Min Act: -0.1700
Data Index: 4362237 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.3257. Min Act: -0.1700
Data Index: 8045002 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.3257. Min Act: -0.1700
Data Index: 4656593 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.2943. Min Act: -0.1700
Data Index: 5952009 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.2629. Min Act: -0.1700
Data Index: 10213 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.2943. Min Act: -0.1700
Data Index: 2121077 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.3257. Min Act: -0.1700
Data Index: 446022 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.2943. Min Act: -0.1700
Data Index: 1975863 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.2943. Min Act: -0.1700
Data Index: 7123746 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.2943. Min Act: -0.1700
Data Index: 6759598 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.2629. Min Act: -0.1700
Data Index: 6736934 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.2943. Min Act: -0.1700
Data Index: 911788 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3885. Min Range: -3.3885
Max Act: 3.2629. Min Act: -0.1700
Data Index: 3443463 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19