Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3746 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.6947. Min Act: -0.1700
Data Index: 7799341 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.6635. Min Act: -0.1700
Data Index: 6987173 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.6322. Min Act: -0.1700
Data Index: 5234240 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.6322. Min Act: -0.1700
Data Index: 3420000 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5697. Min Act: -0.1700
Data Index: 1441674 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5385. Min Act: -0.1700
Data Index: 3892067 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5385. Min Act: -0.1700
Data Index: 683893 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5072. Min Act: -0.1700
Data Index: 1991219 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5072. Min Act: -0.1700
Data Index: 5662851 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4760. Min Act: -0.1700
Data Index: 2888328 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4760. Min Act: -0.1700
Data Index: 1414333 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4760. Min Act: -0.1700
Data Index: 2879843 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4760. Min Act: -0.1700
Data Index: 2876438 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4760. Min Act: -0.1700
Data Index: 5729571 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4447. Min Act: -0.1700
Data Index: 501829 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4760. Min Act: -0.1700
Data Index: 5959816 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4760. Min Act: -0.1700
Data Index: 3633701 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4760. Min Act: -0.1700
Data Index: 6172542 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4760. Min Act: -0.1700
Data Index: 7529690 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4760. Min Act: -0.1700
Data Index: 2671013 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19