Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3293 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1780. Min Range: -6.1780
Max Act: 6.1780. Min Act: -0.1700
Data Index: 6258508 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1780. Min Range: -6.1780
Max Act: 6.1468. Min Act: -0.1700
Data Index: 1164315 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1780. Min Range: -6.1780
Max Act: 6.1155. Min Act: -0.1700
Data Index: 1463161 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1780. Min Range: -6.1780
Max Act: 6.1155. Min Act: -0.1700
Data Index: 1332899 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.9905. Min Act: -0.1700
Data Index: 2688195 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.9593. Min Act: -0.1700
Data Index: 1982397 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.9593. Min Act: -0.1700
Data Index: 5170617 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8968. Min Act: -0.1700
Data Index: 3095545 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8968. Min Act: -0.1700
Data Index: 7575650 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8655. Min Act: -0.1700
Data Index: 3099036 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8655. Min Act: -0.1700
Data Index: 4696879 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8343. Min Act: -0.1700
Data Index: 5884181 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8655. Min Act: -0.1700
Data Index: 6309512 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8343. Min Act: -0.1700
Data Index: 1888084 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8343. Min Act: -0.1700
Data Index: 1363009 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8343. Min Act: -0.1700
Data Index: 884586 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8343. Min Act: -0.1700
Data Index: 5359530 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8030. Min Act: -0.1700
Data Index: 5542402 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8343. Min Act: -0.1700
Data Index: 2056885 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1780. Min Range: -6.1780
Max Act: 5.8030. Min Act: -0.1700
Data Index: 5748064 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19