Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1780 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.4457. Min Act: -0.1700
Data Index: 5344751 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.3516. Min Act: -0.1700
Data Index: 1919483 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.3202. Min Act: -0.1700
Data Index: 4534164 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.3045. Min Act: -0.1700
Data Index: 4922691 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.2888. Min Act: -0.1700
Data Index: 4297051 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.2888. Min Act: -0.1700
Data Index: 1890852 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.2888. Min Act: -0.1700
Data Index: 2119965 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.2260. Min Act: -0.1700
Data Index: 1559001 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.2103. Min Act: -0.1700
Data Index: 2061783 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.2103. Min Act: -0.1700
Data Index: 1005609 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.2260. Min Act: -0.1700
Data Index: 686950 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.1945. Min Act: -0.1700
Data Index: 1507999 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.1945. Min Act: -0.1700
Data Index: 501201 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.1945. Min Act: -0.1700
Data Index: 5324721 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.1945. Min Act: -0.1700
Data Index: 4718203 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.2260. Min Act: -0.1700
Data Index: 3735127 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.1945. Min Act: -0.1700
Data Index: 2523741 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.1788. Min Act: -0.1700
Data Index: 7644943 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.1945. Min Act: -0.1700
Data Index: 5645712 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4457. Min Range: -3.4457
Max Act: 3.1631. Min Act: -0.1700
Data Index: 1156623 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19