Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2990. Min Range: -6.2990
Max Act: 6.2990. Min Act: -0.1700
Data Index: 6375816 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2990. Min Range: -6.2990
Max Act: 6.2053. Min Act: -0.1700
Data Index: 2496044 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2990. Min Range: -6.2990
Max Act: 6.1115. Min Act: -0.1700
Data Index: 1080853 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2990. Min Range: -6.2990
Max Act: 6.1115. Min Act: -0.1700
Data Index: 6083682 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2990. Min Range: -6.2990
Max Act: 6.0803. Min Act: -0.1700
Data Index: 376488 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2990. Min Range: -6.2990
Max Act: 6.0490. Min Act: -0.1700
Data Index: 1177744 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.9553. Min Act: -0.1700
Data Index: 1177745 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.9865. Min Act: -0.1700
Data Index: 8769656 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.9553. Min Act: -0.1700
Data Index: 7588607 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.9240. Min Act: -0.1700
Data Index: 2166143 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.9240. Min Act: -0.1700
Data Index: 5018198 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.9240. Min Act: -0.1700
Data Index: 6186976 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.8928. Min Act: -0.1700
Data Index: 1679005 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.8928. Min Act: -0.1700
Data Index: 7196182 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.8615. Min Act: -0.1700
Data Index: 5866262 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.8615. Min Act: -0.1700
Data Index: 2294620 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.8615. Min Act: -0.1700
Data Index: 12675 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.7990. Min Act: -0.1700
Data Index: 6190366 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.7990. Min Act: -0.1700
Data Index: 3695526 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2990. Min Range: -6.2990
Max Act: 5.7990. Min Act: -0.1700
Data Index: 7130717 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19