Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4767 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.9096. Min Act: -0.1700
Data Index: 646652 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5971. Min Act: -0.1700
Data Index: 8244166 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5346. Min Act: -0.1700
Data Index: 3397478 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5033. Min Act: -0.1700
Data Index: 1898989 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.4721. Min Act: -0.1700
Data Index: 3628943 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5033. Min Act: -0.1700
Data Index: 3836443 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5033. Min Act: -0.1700
Data Index: 935376 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5033. Min Act: -0.1700
Data Index: 427820 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5033. Min Act: -0.1700
Data Index: 7952505 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5033. Min Act: -0.1700
Data Index: 6691636 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5033. Min Act: -0.1700
Data Index: 5888176 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.4721. Min Act: -0.1700
Data Index: 5317315 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.4721. Min Act: -0.1700
Data Index: 8490572 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.4721. Min Act: -0.1700
Data Index: 7238745 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.4721. Min Act: -0.1700
Data Index: 2436509 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.4721. Min Act: -0.1700
Data Index: 2415604 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.4408. Min Act: -0.1700
Data Index: 4241618 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.4721. Min Act: -0.1700
Data Index: 6361521 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.4721. Min Act: -0.1700
Data Index: 6310399 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.4721. Min Act: -0.1700
Data Index: 513531 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19