Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1892 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1281. Min Range: -12.1281
Max Act: 12.1281. Min Act: -0.1700
Data Index: 2863165 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.6281. Min Act: -0.1700
Data Index: 6331860 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.5656. Min Act: -0.1700
Data Index: 59456 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.5031. Min Act: -0.1700
Data Index: 3921529 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.5031. Min Act: -0.1700
Data Index: 2605766 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.5031. Min Act: -0.1700
Data Index: 7539950 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.4406. Min Act: -0.1700
Data Index: 3683530 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.4406. Min Act: -0.1700
Data Index: 5046067 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.3781. Min Act: -0.1700
Data Index: 2802539 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.3781. Min Act: -0.1700
Data Index: 2129426 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.2531. Min Act: -0.1700
Data Index: 4363414 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.3156. Min Act: -0.1700
Data Index: 4008277 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.3156. Min Act: -0.1700
Data Index: 3103262 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.3156. Min Act: -0.1700
Data Index: 7438823 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.3156. Min Act: -0.1700
Data Index: 2957212 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.1906. Min Act: -0.1700
Data Index: 2071108 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.2531. Min Act: -0.1700
Data Index: 2292306 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.2531. Min Act: -0.1700
Data Index: 505685 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.2531. Min Act: -0.1700
Data Index: 1660965 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1281. Min Range: -12.1281
Max Act: 11.2531. Min Act: -0.1700
Data Index: 2901825 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19