Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3836 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.8705. Min Act: -0.1700
Data Index: 2199831 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.8705. Min Act: -0.1700
Data Index: 6751207 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.8393. Min Act: -0.1700
Data Index: 8365598 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.8080. Min Act: -0.1700
Data Index: 7184276 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.7768. Min Act: -0.1700
Data Index: 1397011 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.7455. Min Act: -0.1700
Data Index: 6849046 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.7143. Min Act: -0.1700
Data Index: 292608 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.6518. Min Act: -0.1700
Data Index: 306274 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.6518. Min Act: -0.1700
Data Index: 5412060 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.6205. Min Act: -0.1700
Data Index: 2042541 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.6205. Min Act: -0.1700
Data Index: 6050628 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.5580. Min Act: -0.1700
Data Index: 7114460 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.5580. Min Act: -0.1700
Data Index: 3855720 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.5580. Min Act: -0.1700
Data Index: 4396808 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.4643. Min Act: -0.1700
Data Index: 2931596 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.4643. Min Act: -0.1700
Data Index: 8752725 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.4330. Min Act: -0.1700
Data Index: 3008860 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.4330. Min Act: -0.1700
Data Index: 5950054 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.4018. Min Act: -0.1700
Data Index: 1456122 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8705. Min Range: -7.8705
Max Act: 7.3705. Min Act: -0.1700
Data Index: 8142715 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19