Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3966 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.9099. Min Act: -0.1700
Data Index: 5313533 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.6599. Min Act: -0.1700
Data Index: 2349282 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.6599. Min Act: -0.1700
Data Index: 4310485 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.6599. Min Act: -0.1700
Data Index: 5133023 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.6599. Min Act: -0.1700
Data Index: 6484531 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.6599. Min Act: -0.1700
Data Index: 4956908 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.5974. Min Act: -0.1700
Data Index: 4611409 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.5349. Min Act: -0.1700
Data Index: 1484220 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.5349. Min Act: -0.1700
Data Index: 262848 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.5349. Min Act: -0.1700
Data Index: 2796091 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.4724. Min Act: -0.1700
Data Index: 6696674 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.4099. Min Act: -0.1700
Data Index: 4463925 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.4099. Min Act: -0.1700
Data Index: 883972 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.4099. Min Act: -0.1700
Data Index: 8276531 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.4099. Min Act: -0.1700
Data Index: 5241091 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.4099. Min Act: -0.1700
Data Index: 6962878 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.3474. Min Act: -0.1700
Data Index: 5991418 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.3474. Min Act: -0.1700
Data Index: 1756749 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.2849. Min Act: -0.1700
Data Index: 1729638 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9099. Min Range: -9.9099
Max Act: 9.2849. Min Act: -0.1700
Data Index: 4541901 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19