Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 997 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0908. Min Range: -9.0908
Max Act: 9.0908. Min Act: -0.1700
Data Index: 7803627 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0908. Min Range: -9.0908
Max Act: 9.0908. Min Act: -0.1700
Data Index: 1797318 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.9658. Min Act: -0.1700
Data Index: 1716950 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.9033. Min Act: -0.1700
Data Index: 2141188 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.7783. Min Act: -0.1700
Data Index: 6634474 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.7783. Min Act: -0.1700
Data Index: 330919 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.7158. Min Act: -0.1700
Data Index: 3201084 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.7158. Min Act: -0.1700
Data Index: 4189324 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.7158. Min Act: -0.1700
Data Index: 558421 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.7158. Min Act: -0.1700
Data Index: 4741991 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.7158. Min Act: -0.1700
Data Index: 5029762 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.5908. Min Act: -0.1700
Data Index: 5438327 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.6533. Min Act: -0.1700
Data Index: 5568513 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.6533. Min Act: -0.1700
Data Index: 4840210 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.5908. Min Act: -0.1700
Data Index: 407716 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.5908. Min Act: -0.1700
Data Index: 5307759 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.5908. Min Act: -0.1700
Data Index: 5632935 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.5908. Min Act: -0.1700
Data Index: 1198439 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.5908. Min Act: -0.1700
Data Index: 756501 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0908. Min Range: -9.0908
Max Act: 8.5908. Min Act: -0.1700
Data Index: 939338 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19