Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 825 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.8285. Min Act: -0.1700
Data Index: 3605280 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.7503. Min Act: -0.1700
Data Index: 1222722 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.6721. Min Act: -0.1700
Data Index: 6956603 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.6408. Min Act: -0.1700
Data Index: 4102662 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.6408. Min Act: -0.1700
Data Index: 7734649 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.6251. Min Act: -0.1700
Data Index: 79940 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5938. Min Act: -0.1700
Data Index: 8128711 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5938. Min Act: -0.1700
Data Index: 1507135 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5938. Min Act: -0.1700
Data Index: 5430718 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5625. Min Act: -0.1700
Data Index: 54195 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5625. Min Act: -0.1700
Data Index: 7873881 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5625. Min Act: -0.1700
Data Index: 5560431 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5782. Min Act: -0.1700
Data Index: 3072087 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5469. Min Act: -0.1700
Data Index: 1400636 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5469. Min Act: -0.1700
Data Index: 1400642 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5469. Min Act: -0.1700
Data Index: 1942820 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5312. Min Act: -0.1700
Data Index: 6773358 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5469. Min Act: -0.1700
Data Index: 6798340 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5469. Min Act: -0.1700
Data Index: 5388004 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8285. Min Range: -3.8285
Max Act: 3.5312. Min Act: -0.1700
Data Index: 54196 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19