Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3001 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.9222. Min Act: -0.1700
Data Index: 6249474 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.8910. Min Act: -0.1700
Data Index: 5851150 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.7972. Min Act: -0.1699
Data Index: 289148 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.7660. Min Act: -0.1700
Data Index: 1142458 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.7660. Min Act: -0.1700
Data Index: 8278055 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.7660. Min Act: -0.1700
Data Index: 1362135 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.7347. Min Act: -0.1700
Data Index: 5536484 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.7347. Min Act: -0.1699
Data Index: 5711866 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.7347. Min Act: -0.1700
Data Index: 6221092 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.7035. Min Act: -0.1700
Data Index: 5507855 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.6722. Min Act: -0.1700
Data Index: 605764 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.6722. Min Act: -0.1699
Data Index: 6722959 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.6410. Min Act: -0.1700
Data Index: 7166145 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.6722. Min Act: -0.1700
Data Index: 5805130 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.6410. Min Act: -0.1698
Data Index: 6972302 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.6410. Min Act: -0.1700
Data Index: 605763 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.6097. Min Act: -0.1700
Data Index: 362908 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.6097. Min Act: -0.1700
Data Index: 1486605 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.6097. Min Act: -0.1698
Data Index: 991823 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9222. Min Range: -4.9222
Max Act: 4.5785. Min Act: -0.1700
Data Index: 5970295 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19