Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4798 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5763. Min Range: -7.5763
Max Act: 7.5763. Min Act: -0.1700
Data Index: 5876789 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.7951. Min Act: -0.1700
Data Index: 4823772 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.4513. Min Act: -0.1700
Data Index: 3554298 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.3888. Min Act: -0.1700
Data Index: 2527183 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.4201. Min Act: -0.1700
Data Index: 5174395 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.2951. Min Act: -0.1700
Data Index: 5377739 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.2013. Min Act: -0.1700
Data Index: 4807315 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.1701. Min Act: -0.1700
Data Index: 7391611 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.1701. Min Act: -0.1700
Data Index: 8223148 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.1388. Min Act: -0.1700
Data Index: 5373488 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.1076. Min Act: -0.1700
Data Index: 4140238 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.1076. Min Act: -0.1700
Data Index: 6196751 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.1076. Min Act: -0.1700
Data Index: 7950381 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.1076. Min Act: -0.1700
Data Index: 1408646 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.0763. Min Act: -0.1700
Data Index: 7963724 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.0451. Min Act: -0.1700
Data Index: 6471543 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.0138. Min Act: -0.1700
Data Index: 2647667 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5763. Min Range: -7.5763
Max Act: 6.0138. Min Act: -0.1700
Data Index: 7713668 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5763. Min Range: -7.5763
Max Act: 5.9826. Min Act: -0.1700
Data Index: 1797244 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5763. Min Range: -7.5763
Max Act: 5.9826. Min Act: -0.1700
Data Index: 675996 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19