Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3962 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.6891. Min Act: -0.1700
Data Index: 1863566 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.6891. Min Act: -0.1700
Data Index: 4047426 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.6891. Min Act: -0.1700
Data Index: 5221894 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.6266. Min Act: -0.1700
Data Index: 5904899 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.6266. Min Act: -0.1700
Data Index: 4570306 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.5641. Min Act: -0.1700
Data Index: 1838303 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.5016. Min Act: -0.1700
Data Index: 5902576 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.4704. Min Act: -0.1700
Data Index: 4502869 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.5016. Min Act: -0.1700
Data Index: 5904900 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.5329. Min Act: -0.1700
Data Index: 7326328 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.4704. Min Act: -0.1700
Data Index: 3743688 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.4079. Min Act: -0.1700
Data Index: 8364579 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.3766. Min Act: -0.1700
Data Index: 3394111 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.3766. Min Act: -0.1700
Data Index: 7456965 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.3141. Min Act: -0.1700
Data Index: 4546253 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.2829. Min Act: -0.1700
Data Index: 7277890 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.2829. Min Act: -0.1700
Data Index: 1479203 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.2516. Min Act: -0.1700
Data Index: 6159633 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.1891. Min Act: -0.1700
Data Index: 7074570 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.1891. Min Act: -0.1700
Data Index: 3617744 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19