Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1116. Min Range: -4.1116
Max Act: 4.1116. Min Act: -0.1700
Data Index: 1358179 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.7364. Min Act: -0.1700
Data Index: 5679917 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.7364. Min Act: -0.1700
Data Index: 2402078 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.7051. Min Act: -0.1700
Data Index: 348282 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.6895. Min Act: -0.1700
Data Index: 5522687 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.6582. Min Act: -0.1700
Data Index: 7141783 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.6582. Min Act: -0.1700
Data Index: 8160836 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.6582. Min Act: -0.1700
Data Index: 8354160 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.6269. Min Act: -0.1700
Data Index: 7659206 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.6426. Min Act: -0.1700
Data Index: 144390 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.6426. Min Act: -0.1700
Data Index: 7223968 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.6426. Min Act: -0.1700
Data Index: 2079377 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.6269. Min Act: -0.1700
Data Index: 4802230 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.5800. Min Act: -0.1700
Data Index: 7727651 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.5956. Min Act: -0.1700
Data Index: 4861912 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.5956. Min Act: -0.1700
Data Index: 2075917 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.5800. Min Act: -0.1700
Data Index: 1211375 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.5800. Min Act: -0.1700
Data Index: 5648098 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.5800. Min Act: -0.1700
Data Index: 7789457 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1116. Min Range: -4.1116
Max Act: 3.5643. Min Act: -0.1700
Data Index: 5079982 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19