Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3475. Min Range: -8.3475
Max Act: 8.3475. Min Act: -0.1700
Data Index: 241637 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3475. Min Range: -8.3475
Max Act: 8.1912. Min Act: -0.1700
Data Index: 7784290 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3475. Min Range: -8.3475
Max Act: 8.1912. Min Act: -0.1700
Data Index: 1267825 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3475. Min Range: -8.3475
Max Act: 8.0037. Min Act: -0.1700
Data Index: 7833075 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.9412. Min Act: -0.1700
Data Index: 7856197 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.9412. Min Act: -0.1700
Data Index: 4547675 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.9100. Min Act: -0.1700
Data Index: 6912673 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.8475. Min Act: -0.1700
Data Index: 6016911 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.8162. Min Act: -0.1700
Data Index: 1220395 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.7850. Min Act: -0.1700
Data Index: 7981715 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.8162. Min Act: -0.1700
Data Index: 3222241 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.8162. Min Act: -0.1700
Data Index: 2103719 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.7850. Min Act: -0.1700
Data Index: 477121 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.7850. Min Act: -0.1700
Data Index: 5764811 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.7850. Min Act: -0.1700
Data Index: 7028155 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.6912. Min Act: -0.1700
Data Index: 2265469 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.7225. Min Act: -0.1700
Data Index: 998758 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.7225. Min Act: -0.1700
Data Index: 7037369 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.6912. Min Act: -0.1700
Data Index: 4423623 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3475. Min Range: -8.3475
Max Act: 7.6912. Min Act: -0.1700
Data Index: 2642615 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19