Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.1835. Min Act: -0.1700
Data Index: 5145825 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.1363. Min Act: -0.1700
Data Index: 5897018 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.1048. Min Act: -0.1700
Data Index: 8149962 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0890. Min Act: -0.1700
Data Index: 2417435 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0890. Min Act: -0.1700
Data Index: 1061405 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0890. Min Act: -0.1700
Data Index: 5145827 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0575. Min Act: -0.1700
Data Index: 6539841 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0417. Min Act: -0.1700
Data Index: 316602 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0259. Min Act: -0.1700
Data Index: 8491559 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0259. Min Act: -0.1700
Data Index: 4256124 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0101. Min Act: -0.1700
Data Index: 4324079 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0101. Min Act: -0.1700
Data Index: 5152097 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0101. Min Act: -0.1700
Data Index: 8019722 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0101. Min Act: -0.1700
Data Index: 316599 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0101. Min Act: -0.1700
Data Index: 5164824 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0101. Min Act: -0.1700
Data Index: 3727243 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0101. Min Act: -0.1700
Data Index: 23190 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0101. Min Act: -0.1700
Data Index: 2295778 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1835. Min Range: -3.1835
Max Act: 3.0101. Min Act: -0.1700
Data Index: 2275082 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1835. Min Range: -3.1835
Max Act: 2.9943. Min Act: -0.1700
Data Index: 7108721 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19