Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4442 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5771. Min Range: -6.5771
Max Act: 6.5771. Min Act: -0.1700
Data Index: 8074209 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5771. Min Range: -6.5771
Max Act: 6.1396. Min Act: -0.1700
Data Index: 5418558 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5771. Min Range: -6.5771
Max Act: 6.0771. Min Act: -0.1700
Data Index: 307654 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5771. Min Range: -6.5771
Max Act: 6.0459. Min Act: -0.1700
Data Index: 5779423 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5771. Min Range: -6.5771
Max Act: 6.0146. Min Act: -0.1700
Data Index: 5653173 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5771. Min Range: -6.5771
Max Act: 6.0146. Min Act: -0.1700
Data Index: 3330335 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.9834. Min Act: -0.1700
Data Index: 2498778 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.8896. Min Act: -0.1700
Data Index: 699592 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.8896. Min Act: -0.1700
Data Index: 1671514 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.8584. Min Act: -0.1700
Data Index: 5818349 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.8584. Min Act: -0.1700
Data Index: 2265372 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.8271. Min Act: -0.1700
Data Index: 286974 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.8271. Min Act: -0.1700
Data Index: 4843692 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.7959. Min Act: -0.1700
Data Index: 1643722 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.7646. Min Act: -0.1700
Data Index: 7625186 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.7646. Min Act: -0.1700
Data Index: 4915542 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.7646. Min Act: -0.1700
Data Index: 1606498 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.7021. Min Act: -0.1700
Data Index: 7576720 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.7334. Min Act: -0.1700
Data Index: 2163021 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5771. Min Range: -6.5771
Max Act: 5.7334. Min Act: -0.1700
Data Index: 7002289 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19