Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3402 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6530. Min Act: -0.1700
Data Index: 3715896 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6843. Min Act: -0.1700
Data Index: 1023716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6843. Min Act: -0.1700
Data Index: 2479496 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6530. Min Act: -0.1700
Data Index: 3484220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6530. Min Act: -0.1700
Data Index: 6632431 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6530. Min Act: -0.1700
Data Index: 7606984 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 1711455 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 81836 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 2428519 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 942861 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 1948443 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 1914093 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 593039 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 1642052 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 861784 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 214491 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 1626720 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 1299221 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 807250 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6843. Min Range: -3.6843
Max Act: 3.6217. Min Act: -0.1700
Data Index: 1222778 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19