Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3956 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.6878. Min Act: -0.1683
Data Index: 4132684 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.6182. Min Act: -0.1698
Data Index: 5663063 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.6182. Min Act: -0.1700
Data Index: 365910 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.6095. Min Act: -0.1700
Data Index: 3948953 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.6095. Min Act: -0.1700
Data Index: 5534426 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5833. Min Act: -0.1694
Data Index: 4132683 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5833. Min Act: -0.1700
Data Index: 5059391 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.6008. Min Act: -0.1698
Data Index: 6227476 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5745. Min Act: -0.1699
Data Index: 7192287 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5920. Min Act: -0.1695
Data Index: 8485111 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5570. Min Act: -0.1695
Data Index: 6795831 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5745. Min Act: -0.1694
Data Index: 8604936 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5570. Min Act: -0.1699
Data Index: 2418967 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5483. Min Act: -0.1700
Data Index: 2783840 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5483. Min Act: -0.1695
Data Index: 5534425 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5483. Min Act: -0.1700
Data Index: 3310583 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5483. Min Act: -0.1689
Data Index: 8111878 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5395. Min Act: -0.1700
Data Index: 6948781 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5395. Min Act: -0.1700
Data Index: 8270290 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6878. Min Range: -1.6878
Max Act: 1.5395. Min Act: -0.1700
Data Index: 3816670 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19