Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 487 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.6760. Min Act: -0.1700
Data Index: 1805208 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.6447. Min Act: -0.1700
Data Index: 8366062 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.4411. Min Act: -0.1700
Data Index: 2576345 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.4098. Min Act: -0.1700
Data Index: 1813362 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.3313. Min Act: -0.1700
Data Index: 6586663 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.3784. Min Act: -0.1700
Data Index: 6154554 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.3313. Min Act: -0.1700
Data Index: 8374893 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.3156. Min Act: -0.1700
Data Index: 3524587 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.3156. Min Act: -0.1700
Data Index: 579870 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.3156. Min Act: -0.1700
Data Index: 6044757 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.2685. Min Act: -0.1700
Data Index: 2827684 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.2528. Min Act: -0.1700
Data Index: 2797319 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.2685. Min Act: -0.1700
Data Index: 6819463 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.2685. Min Act: -0.1700
Data Index: 4133767 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.2685. Min Act: -0.1700
Data Index: 6344365 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.2371. Min Act: -0.1700
Data Index: 7381158 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.2214. Min Act: -0.1700
Data Index: 5558331 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.2371. Min Act: -0.1700
Data Index: 4215793 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.2371. Min Act: -0.1700
Data Index: 799431 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6760. Min Range: -3.6760
Max Act: 3.2214. Min Act: -0.1700
Data Index: 6217777 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19