Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3249 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3488. Min Range: -8.3488
Max Act: 8.3488. Min Act: -0.1700
Data Index: 8082628 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3488. Min Range: -8.3488
Max Act: 8.0988. Min Act: -0.1700
Data Index: 8050655 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3488. Min Range: -8.3488
Max Act: 8.0363. Min Act: -0.1700
Data Index: 7977694 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.9738. Min Act: -0.1700
Data Index: 2431462 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3488. Min Range: -8.3488
Max Act: 8.0363. Min Act: -0.1700
Data Index: 7041559 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.9113. Min Act: -0.1700
Data Index: 4179270 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.9113. Min Act: -0.1700
Data Index: 446342 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.8488. Min Act: -0.1700
Data Index: 6503841 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.7238. Min Act: -0.1700
Data Index: 1893005 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.7238. Min Act: -0.1700
Data Index: 4141977 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.6613. Min Act: -0.1700
Data Index: 677311 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.6613. Min Act: -0.1700
Data Index: 5373070 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.6613. Min Act: -0.1700
Data Index: 480274 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.6300. Min Act: -0.1700
Data Index: 6426412 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.6300. Min Act: -0.1700
Data Index: 8773829 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.6300. Min Act: -0.1700
Data Index: 5228547 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.6300. Min Act: -0.1700
Data Index: 1768598 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.5988. Min Act: -0.1700
Data Index: 6570257 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.5988. Min Act: -0.1700
Data Index: 3463699 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3488. Min Range: -8.3488
Max Act: 7.5988. Min Act: -0.1700
Data Index: 2868404 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19