Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5740 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.6470. Min Act: -0.1700
Data Index: 5734619 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.5220. Min Act: -0.1700
Data Index: 3029492 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.4595. Min Act: -0.1700
Data Index: 1006740 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.5220. Min Act: -0.1700
Data Index: 3275952 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.3970. Min Act: -0.1700
Data Index: 655887 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.3970. Min Act: -0.1699
Data Index: 6062194 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.3970. Min Act: -0.1700
Data Index: 191429 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.3345. Min Act: -0.1700
Data Index: 7641513 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.3345. Min Act: -0.1700
Data Index: 4900063 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.2720. Min Act: -0.1700
Data Index: 2009982 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.3345. Min Act: -0.1700
Data Index: 4973497 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.3345. Min Act: -0.1700
Data Index: 8735625 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.3970. Min Act: -0.1700
Data Index: 7862110 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.2720. Min Act: -0.1700
Data Index: 91068 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.2720. Min Act: -0.1700
Data Index: 2549696 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.2720. Min Act: -0.1700
Data Index: 1679346 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.2720. Min Act: -0.1700
Data Index: 648606 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.2720. Min Act: -0.1700
Data Index: 6433113 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.2720. Min Act: -0.1700
Data Index: 1685457 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.2720. Min Act: -0.1700
Data Index: 6604337 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19