Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5560 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.2402. Min Act: -0.1700
Data Index: 1772952 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.1465. Min Act: -0.1700
Data Index: 968988 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.1777. Min Act: -0.1700
Data Index: 6114842 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.1465. Min Act: -0.1700
Data Index: 4864844 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.1465. Min Act: -0.1700
Data Index: 1753093 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.1152. Min Act: -0.1700
Data Index: 7866298 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.1152. Min Act: -0.1700
Data Index: 8543914 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0840. Min Act: -0.1700
Data Index: 159719 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0840. Min Act: -0.1700
Data Index: 4849854 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0527. Min Act: -0.1700
Data Index: 4117225 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0527. Min Act: -0.1700
Data Index: 8340658 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0527. Min Act: -0.1700
Data Index: 4292508 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0527. Min Act: -0.1700
Data Index: 4292509 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0527. Min Act: -0.1700
Data Index: 591003 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0215. Min Act: -0.1700
Data Index: 3774117 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0215. Min Act: -0.1700
Data Index: 7816554 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0215. Min Act: -0.1700
Data Index: 1032813 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0527. Min Act: -0.1700
Data Index: 8152012 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2402. Min Range: -5.2402
Max Act: 5.0215. Min Act: -0.1700
Data Index: 4104717 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2402. Min Range: -5.2402
Max Act: 4.9902. Min Act: -0.1700
Data Index: 4157663 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19