Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.3683. Min Act: -0.1700
Data Index: 8734281 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.3370. Min Act: -0.1700
Data Index: 674702 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.2433. Min Act: -0.1700
Data Index: 930532 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.2433. Min Act: -0.1700
Data Index: 2667643 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.2120. Min Act: -0.1700
Data Index: 4293356 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1495. Min Act: -0.1700
Data Index: 7868331 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1808. Min Act: -0.1700
Data Index: 2295236 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1808. Min Act: -0.1700
Data Index: 5935387 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1808. Min Act: -0.1700
Data Index: 5392896 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1495. Min Act: -0.1700
Data Index: 6639426 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1495. Min Act: -0.1700
Data Index: 4591592 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1183. Min Act: -0.1700
Data Index: 1023992 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1183. Min Act: -0.1700
Data Index: 2245211 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1183. Min Act: -0.1700
Data Index: 609217 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1183. Min Act: -0.1700
Data Index: 758894 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1183. Min Act: -0.1700
Data Index: 3210813 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.1183. Min Act: -0.1700
Data Index: 2691518 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.0558. Min Act: -0.1700
Data Index: 5392895 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.0870. Min Act: -0.1700
Data Index: 5303704 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3683. Min Range: -5.3683
Max Act: 5.0870. Min Act: -0.1700
Data Index: 7156462 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19