Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 757 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.6277. Min Act: -0.1700
Data Index: 7105893 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.5652. Min Act: -0.1700
Data Index: 4625647 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.5652. Min Act: -0.1700
Data Index: 1841366 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.5340. Min Act: -0.1700
Data Index: 2206683 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.5027. Min Act: -0.1700
Data Index: 7980456 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.5340. Min Act: -0.1700
Data Index: 2916407 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.5027. Min Act: -0.1700
Data Index: 8561601 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.5027. Min Act: -0.1700
Data Index: 8206072 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.5027. Min Act: -0.1700
Data Index: 8015347 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.5027. Min Act: -0.1700
Data Index: 3047599 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.4090. Min Act: -0.1700
Data Index: 8316655 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.4402. Min Act: -0.1700
Data Index: 7354443 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.4090. Min Act: -0.1700
Data Index: 3052631 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.4090. Min Act: -0.1700
Data Index: 6617688 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.4090. Min Act: -0.1700
Data Index: 3984904 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.4090. Min Act: -0.1700
Data Index: 6865615 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.3777. Min Act: -0.1700
Data Index: 6645663 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.4090. Min Act: -0.1700
Data Index: 574939 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.3465. Min Act: -0.1700
Data Index: 1607099 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6277. Min Range: -5.6277
Max Act: 5.3777. Min Act: -0.1700
Data Index: 6555201 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19