Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2401 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.2398. Min Act: -0.1700
Data Index: 6466022 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.1148. Min Act: -0.1700
Data Index: 7327068 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.1460. Min Act: -0.1700
Data Index: 3767252 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.1460. Min Act: -0.1700
Data Index: 5997884 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.1148. Min Act: -0.1700
Data Index: 5435259 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.0523. Min Act: -0.1700
Data Index: 727607 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.0210. Min Act: -0.1700
Data Index: 7720289 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.0210. Min Act: -0.1700
Data Index: 4011251 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9585. Min Act: -0.1700
Data Index: 4524091 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.0523. Min Act: -0.1700
Data Index: 893390 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9898. Min Act: -0.1700
Data Index: 691676 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9898. Min Act: -0.1700
Data Index: 4506489 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9898. Min Act: -0.1700
Data Index: 3767253 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9898. Min Act: -0.1700
Data Index: 600090 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9585. Min Act: -0.1700
Data Index: 3558321 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9898. Min Act: -0.1700
Data Index: 4258877 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.0210. Min Act: -0.1700
Data Index: 7569124 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9585. Min Act: -0.1700
Data Index: 368567 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9273. Min Act: -0.1700
Data Index: 1305805 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9585. Min Act: -0.1700
Data Index: 2666794 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19