Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 740 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1834. Min Act: -0.1700
Data Index: 3527424 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1668. Min Act: -0.1700
Data Index: 5004034 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1668. Min Act: -0.1700
Data Index: 348811 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1502. Min Act: -0.1700
Data Index: 1463807 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1502. Min Act: -0.1700
Data Index: 8269516 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1668. Min Act: -0.1700
Data Index: 7743694 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1502. Min Act: -0.1700
Data Index: 6991844 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1502. Min Act: -0.1700
Data Index: 3771089 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1335. Min Act: -0.1700
Data Index: 6161438 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1168. Min Act: -0.1700
Data Index: 8798194 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1335. Min Act: -0.1700
Data Index: 376723 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1335. Min Act: -0.1700
Data Index: 3362374 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1168. Min Act: -0.1700
Data Index: 6307752 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1168. Min Act: -0.1700
Data Index: 382431 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1168. Min Act: -0.1700
Data Index: 1045434 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1335. Min Act: -0.1700
Data Index: 7235937 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1168. Min Act: -0.1700
Data Index: 4498844 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1000. Min Act: -0.1700
Data Index: 1774035 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1000. Min Act: -0.1700
Data Index: 5425521 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1834. Min Range: -2.1834
Max Act: 2.1000. Min Act: -0.1700
Data Index: 2357899 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19