Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.5208. Min Act: -0.1700
Data Index: 5848532 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4856. Min Act: -0.1700
Data Index: 5882084 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4856. Min Act: -0.1700
Data Index: 6507803 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4681. Min Act: -0.1700
Data Index: 5047161 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4593. Min Act: -0.1700
Data Index: 1982967 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4769. Min Act: -0.1700
Data Index: 6630736 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4593. Min Act: -0.1700
Data Index: 5552052 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4593. Min Act: -0.1700
Data Index: 345220 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4593. Min Act: -0.1700
Data Index: 4471480 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4505. Min Act: -0.1700
Data Index: 5358675 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4505. Min Act: -0.1700
Data Index: 8764052 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4505. Min Act: -0.1700
Data Index: 1183741 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4329. Min Act: -0.1700
Data Index: 2008636 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4505. Min Act: -0.1700
Data Index: 2328840 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4417. Min Act: -0.1700
Data Index: 6506809 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4417. Min Act: -0.1700
Data Index: 1686981 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4417. Min Act: -0.1700
Data Index: 3829447 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4329. Min Act: -0.1700
Data Index: 3473466 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4329. Min Act: -0.1700
Data Index: 2141991 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4241. Min Act: -0.1700
Data Index: 5196801 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19