Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0344. Min Range: -3.0344
Max Act: 3.0344. Min Act: -0.1700
Data Index: 1375797 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.9237. Min Act: -0.1700
Data Index: 5218635 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.9237. Min Act: -0.1700
Data Index: 3624122 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.9079. Min Act: -0.1700
Data Index: 8210815 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.9079. Min Act: -0.1700
Data Index: 7734885 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8602. Min Act: -0.1700
Data Index: 1861145 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8444. Min Act: -0.1700
Data Index: 2238172 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8444. Min Act: -0.1700
Data Index: 5727965 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8444. Min Act: -0.1700
Data Index: 6667137 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8444. Min Act: -0.1700
Data Index: 1774807 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8444. Min Act: -0.1700
Data Index: 6236355 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8444. Min Act: -0.1700
Data Index: 8826778 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8444. Min Act: -0.1700
Data Index: 7434873 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8126. Min Act: -0.1700
Data Index: 795588 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8444. Min Act: -0.1700
Data Index: 5737620 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8285. Min Act: -0.1700
Data Index: 4697093 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8285. Min Act: -0.1700
Data Index: 7566989 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8126. Min Act: -0.1700
Data Index: 81915 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8126. Min Act: -0.1700
Data Index: 5551246 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0344. Min Range: -3.0344
Max Act: 2.8126. Min Act: -0.1700
Data Index: 8672906 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19