Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.7276. Min Act: -0.1700
Data Index: 8270266 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.6338. Min Act: -0.1700
Data Index: 7704536 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.5713. Min Act: -0.1700
Data Index: 847101 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.5713. Min Act: -0.1700
Data Index: 5755442 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.5713. Min Act: -0.1700
Data Index: 7293046 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.5401. Min Act: -0.1700
Data Index: 5665116 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.5401. Min Act: -0.1700
Data Index: 4515453 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.5088. Min Act: -0.1700
Data Index: 618657 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.5088. Min Act: -0.1700
Data Index: 5979358 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.5088. Min Act: -0.1700
Data Index: 6066606 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.4776. Min Act: -0.1700
Data Index: 2621279 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.4776. Min Act: -0.1700
Data Index: 6900626 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.4776. Min Act: -0.1700
Data Index: 3058946 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.4463. Min Act: -0.1700
Data Index: 431712 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.4151. Min Act: -0.1700
Data Index: 6517442 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.4151. Min Act: -0.1700
Data Index: 8447416 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.4151. Min Act: -0.1700
Data Index: 5451588 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.4151. Min Act: -0.1700
Data Index: 1749243 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.4151. Min Act: -0.1700
Data Index: 6336190 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7276. Min Range: -6.7276
Max Act: 6.3838. Min Act: -0.1700
Data Index: 7022523 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19