Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.7079. Min Act: -0.1700
Data Index: 4307603 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.6766. Min Act: -0.1700
Data Index: 30938 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.5829. Min Act: -0.1700
Data Index: 7590684 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.5829. Min Act: -0.1700
Data Index: 4514492 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.5516. Min Act: -0.1700
Data Index: 2461154 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.5516. Min Act: -0.1700
Data Index: 701015 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.5516. Min Act: -0.1700
Data Index: 641798 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.5204. Min Act: -0.1700
Data Index: 7590689 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.5516. Min Act: -0.1700
Data Index: 5615890 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.5204. Min Act: -0.1700
Data Index: 8650738 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.5204. Min Act: -0.1700
Data Index: 4859460 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.5204. Min Act: -0.1700
Data Index: 8575281 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.5204. Min Act: -0.1700
Data Index: 6500793 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.4891. Min Act: -0.1700
Data Index: 990875 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.4891. Min Act: -0.1700
Data Index: 6622834 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.4891. Min Act: -0.1700
Data Index: 1112881 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.3641. Min Act: -0.1700
Data Index: 3118951 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.3329. Min Act: -0.1700
Data Index: 445127 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.3016. Min Act: -0.1700
Data Index: 7590674 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7079. Min Range: -5.7079
Max Act: 5.2704. Min Act: -0.1700
Data Index: 1992475 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19