Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 413 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.3106. Min Act: -0.1700
Data Index: 4687733 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2941. Min Act: -0.1700
Data Index: 3144246 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2777. Min Act: -0.1700
Data Index: 5501277 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2612. Min Act: -0.1700
Data Index: 7935339 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2612. Min Act: -0.1700
Data Index: 1363087 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2447. Min Act: -0.1700
Data Index: 403524 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2612. Min Act: -0.1700
Data Index: 6080153 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2447. Min Act: -0.1700
Data Index: 721715 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2447. Min Act: -0.1700
Data Index: 4754975 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2612. Min Act: -0.1700
Data Index: 7378374 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2447. Min Act: -0.1700
Data Index: 1972920 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2447. Min Act: -0.1700
Data Index: 1865723 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2281. Min Act: -0.1700
Data Index: 3237896 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2447. Min Act: -0.1700
Data Index: 771403 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2115. Min Act: -0.1700
Data Index: 5330819 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2115. Min Act: -0.1700
Data Index: 5905250 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2115. Min Act: -0.1700
Data Index: 4597978 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2281. Min Act: -0.1700
Data Index: 7676855 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.2115. Min Act: -0.1700
Data Index: 5856260 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3106. Min Range: -2.3106
Max Act: 2.1950. Min Act: -0.1700
Data Index: 5843226 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19