Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1783 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1059. Min Range: -7.1059
Max Act: 7.1059. Min Act: -0.1700
Data Index: 2516748 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1059. Min Range: -7.1059
Max Act: 7.0434. Min Act: -0.1700
Data Index: 7878613 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1059. Min Range: -7.1059
Max Act: 7.0434. Min Act: -0.1700
Data Index: 6908684 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1059. Min Range: -7.1059
Max Act: 7.0122. Min Act: -0.1700
Data Index: 6173687 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.9809. Min Act: -0.1700
Data Index: 8480495 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.9497. Min Act: -0.1700
Data Index: 7623602 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.8872. Min Act: -0.1700
Data Index: 8589356 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.7934. Min Act: -0.1700
Data Index: 144958 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.8247. Min Act: -0.1700
Data Index: 4024192 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.7622. Min Act: -0.1700
Data Index: 7980325 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.6997. Min Act: -0.1700
Data Index: 3347979 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.6684. Min Act: -0.1700
Data Index: 4239945 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.6997. Min Act: -0.1700
Data Index: 6792585 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.6684. Min Act: -0.1700
Data Index: 5491833 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.6372. Min Act: -0.1700
Data Index: 4457320 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.6059. Min Act: -0.1700
Data Index: 2034488 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.6059. Min Act: -0.1700
Data Index: 3460749 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.6059. Min Act: -0.1700
Data Index: 8793586 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.5747. Min Act: -0.1700
Data Index: 8161404 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1059. Min Range: -7.1059
Max Act: 6.5747. Min Act: -0.1700
Data Index: 5509881 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19