Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4703 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.6683. Min Act: -0.1700
Data Index: 5852700 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.6370. Min Act: -0.1700
Data Index: 2951461 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.6213. Min Act: -0.1700
Data Index: 4304357 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.6057. Min Act: -0.1700
Data Index: 7472485 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.6057. Min Act: -0.1700
Data Index: 3370467 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.5744. Min Act: -0.1700
Data Index: 5220905 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.5587. Min Act: -0.1700
Data Index: 5627232 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.5274. Min Act: -0.1700
Data Index: 2958109 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.5274. Min Act: -0.1700
Data Index: 6293799 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.5431. Min Act: -0.1700
Data Index: 5496050 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.5274. Min Act: -0.1700
Data Index: 200193 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.5118. Min Act: -0.1700
Data Index: 435726 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.5274. Min Act: -0.1700
Data Index: 7819870 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.5118. Min Act: -0.1700
Data Index: 4335418 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.5118. Min Act: -0.1700
Data Index: 1020319 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.4961. Min Act: -0.1700
Data Index: 109249 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.4804. Min Act: -0.1700
Data Index: 6288365 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.4804. Min Act: -0.1700
Data Index: 4062243 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.4804. Min Act: -0.1700
Data Index: 1413604 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6683. Min Range: -3.6683
Max Act: 3.4804. Min Act: -0.1700
Data Index: 2233899 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19