Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2232. Min Act: -0.1700
Data Index: 4150003 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1698
Data Index: 5345129 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1693
Data Index: 5986986 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1693
Data Index: 3397018 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1700
Data Index: 1120412 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1700
Data Index: 2013917 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1700
Data Index: 1896041 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1700
Data Index: 6339719 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1700
Data Index: 77833 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1699
Data Index: 382088 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1698
Data Index: 4333192 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1693
Data Index: 1561840 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1693
Data Index: 3222677 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1700
Data Index: 6801446 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1695
Data Index: 6599565 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1700
Data Index: 6774388 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1693
Data Index: 2599695 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1700
Data Index: 6179585 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1693
Data Index: 6343204 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2232. Min Range: -0.2232
Max Act: 0.2054. Min Act: -0.1700
Data Index: 2965808 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19