Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1682 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0434. Min Range: -6.0434
Max Act: 6.0434. Min Act: -0.1700
Data Index: 7949229 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0434. Min Range: -6.0434
Max Act: 6.0121. Min Act: -0.1700
Data Index: 8404177 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0434. Min Range: -6.0434
Max Act: 6.0121. Min Act: -0.1700
Data Index: 2110678 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.9809. Min Act: -0.1700
Data Index: 5458271 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.9496. Min Act: -0.1700
Data Index: 5302849 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.9184. Min Act: -0.1700
Data Index: 8238926 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.9184. Min Act: -0.1700
Data Index: 6235163 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.8246. Min Act: -0.1700
Data Index: 1072277 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.7934. Min Act: -0.1700
Data Index: 7226412 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.8559. Min Act: -0.1700
Data Index: 6404498 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.7934. Min Act: -0.1700
Data Index: 7838460 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.7934. Min Act: -0.1700
Data Index: 4827577 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.7934. Min Act: -0.1700
Data Index: 685254 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.7621. Min Act: -0.1700
Data Index: 2194154 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.7621. Min Act: -0.1700
Data Index: 941936 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.7309. Min Act: -0.1700
Data Index: 6054723 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.7309. Min Act: -0.1700
Data Index: 636079 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.6996. Min Act: -0.1700
Data Index: 2895458 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.6996. Min Act: -0.1700
Data Index: 1239518 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0434. Min Range: -6.0434
Max Act: 5.6996. Min Act: -0.1700
Data Index: 3752545 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19