Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 776 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2043. Min Range: -6.2043
Max Act: 6.2043. Min Act: -0.1700
Data Index: 8145741 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2043. Min Range: -6.2043
Max Act: 6.0793. Min Act: -0.1700
Data Index: 4777370 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2043. Min Range: -6.2043
Max Act: 6.1105. Min Act: -0.1700
Data Index: 4414941 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.9543. Min Act: -0.1700
Data Index: 7865911 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.8605. Min Act: -0.1700
Data Index: 2982187 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.7043. Min Act: -0.1700
Data Index: 4966960 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.6730. Min Act: -0.1700
Data Index: 5534137 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.6105. Min Act: -0.1700
Data Index: 4923623 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.6418. Min Act: -0.1700
Data Index: 4931860 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.6418. Min Act: -0.1700
Data Index: 1220659 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.6418. Min Act: -0.1700
Data Index: 2002528 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.5793. Min Act: -0.1700
Data Index: 7845531 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.5793. Min Act: -0.1700
Data Index: 146417 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.5480. Min Act: -0.1700
Data Index: 4357339 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.5480. Min Act: -0.1700
Data Index: 2043185 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 7614698 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 8248342 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 7580686 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 342382 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2043. Min Range: -6.2043
Max Act: 5.4855. Min Act: -0.1700
Data Index: 6933934 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19