Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2092 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.6433. Min Act: -0.1700
Data Index: 5238768 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.6433. Min Act: -0.1700
Data Index: 3125126 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.5494. Min Act: -0.1700
Data Index: 4159215 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.5494. Min Act: -0.1700
Data Index: 3310786 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.5181. Min Act: -0.1700
Data Index: 2813471 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.3300. Min Act: -0.1700
Data Index: 557725 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.3300. Min Act: -0.1700
Data Index: 6344655 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.2986. Min Act: -0.1700
Data Index: 2161101 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.2986. Min Act: -0.1700
Data Index: 7821876 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.2986. Min Act: -0.1700
Data Index: 8488850 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.2672. Min Act: -0.1700
Data Index: 4617048 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.2358. Min Act: -0.1700
Data Index: 2802752 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.2672. Min Act: -0.1700
Data Index: 6544932 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.2358. Min Act: -0.1700
Data Index: 57937 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.2043. Min Act: -0.1700
Data Index: 6663092 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.1886. Min Act: -0.1700
Data Index: 1591032 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.1729. Min Act: -0.1700
Data Index: 4074757 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.1886. Min Act: -0.1700
Data Index: 7341842 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.1886. Min Act: -0.1700
Data Index: 567652 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6433. Min Range: -3.6433
Max Act: 3.1729. Min Act: -0.1700
Data Index: 5479847 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19