Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 273 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3398. Min Range: -6.3398
Max Act: 6.3398. Min Act: -0.1700
Data Index: 7319224 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3398. Min Range: -6.3398
Max Act: 6.3085. Min Act: -0.1700
Data Index: 6162073 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3398. Min Range: -6.3398
Max Act: 6.2460. Min Act: -0.1700
Data Index: 264587 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3398. Min Range: -6.3398
Max Act: 6.1835. Min Act: -0.1700
Data Index: 8715086 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3398. Min Range: -6.3398
Max Act: 6.1835. Min Act: -0.1700
Data Index: 3205487 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3398. Min Range: -6.3398
Max Act: 6.1523. Min Act: -0.1700
Data Index: 5680108 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3398. Min Range: -6.3398
Max Act: 6.0585. Min Act: -0.1700
Data Index: 3846790 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3398. Min Range: -6.3398
Max Act: 6.0898. Min Act: -0.1700
Data Index: 4415706 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3398. Min Range: -6.3398
Max Act: 6.0273. Min Act: -0.1700
Data Index: 1465391 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3398. Min Range: -6.3398
Max Act: 5.9335. Min Act: -0.1700
Data Index: 1668020 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3398. Min Range: -6.3398
Max Act: 5.8710. Min Act: -0.1700
Data Index: 4096350 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3398. Min Range: -6.3398
Max Act: 5.8398. Min Act: -0.1700
Data Index: 8801731 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3398. Min Range: -6.3398
Max Act: 5.8710. Min Act: -0.1700
Data Index: 3179963 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3398. Min Range: -6.3398
Max Act: 5.8710. Min Act: -0.1700
Data Index: 7065276 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3398. Min Range: -6.3398
Max Act: 5.8710. Min Act: -0.1700
Data Index: 8045959 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3398. Min Range: -6.3398
Max Act: 5.8710. Min Act: -0.1700
Data Index: 169713 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3398. Min Range: -6.3398
Max Act: 5.8398. Min Act: -0.1700
Data Index: 3552124 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3398. Min Range: -6.3398
Max Act: 5.8085. Min Act: -0.1700
Data Index: 1114806 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3398. Min Range: -6.3398
Max Act: 5.8085. Min Act: -0.1700
Data Index: 6540889 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3398. Min Range: -6.3398
Max Act: 5.8398. Min Act: -0.1700
Data Index: 6491669 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19