Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 857 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.2323. Min Act: -0.1700
Data Index: 8431737 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1991. Min Act: -0.1700
Data Index: 7237663 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1825. Min Act: -0.1700
Data Index: 4025768 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1825. Min Act: -0.1700
Data Index: 1362479 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1825. Min Act: -0.1699
Data Index: 7237655 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1825. Min Act: -0.1700
Data Index: 7237665 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1659. Min Act: -0.1700
Data Index: 631119 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1825. Min Act: -0.1700
Data Index: 664877 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1659. Min Act: -0.1699
Data Index: 7636910 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1492. Min Act: -0.1700
Data Index: 7453240 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1659. Min Act: -0.1700
Data Index: 3165625 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1492. Min Act: -0.1700
Data Index: 6248939 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1492. Min Act: -0.1700
Data Index: 3165623 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1659. Min Act: -0.1697
Data Index: 4158420 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1659. Min Act: -0.1700
Data Index: 3165624 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1492. Min Act: -0.1700
Data Index: 291114 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1492. Min Act: -0.1700
Data Index: 4043338 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1492. Min Act: -0.1700
Data Index: 7237662 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1492. Min Act: -0.1699
Data Index: 8189717 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2323. Min Range: -2.2323
Max Act: 2.1492. Min Act: -0.1700
Data Index: 2942203 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19