Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 313 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.8745. Min Act: -0.1700
Data Index: 404059 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.7182. Min Act: -0.1700
Data Index: 4011827 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.5307. Min Act: -0.1700
Data Index: 3184663 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.5620. Min Act: -0.1700
Data Index: 7422229 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.5307. Min Act: -0.1700
Data Index: 4350189 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.5307. Min Act: -0.1696
Data Index: 2876686 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.5307. Min Act: -0.1700
Data Index: 956784 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.5307. Min Act: -0.1700
Data Index: 3380736 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4995. Min Act: -0.1695
Data Index: 1937292 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4682. Min Act: -0.1700
Data Index: 8047370 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4370. Min Act: -0.1700
Data Index: 1352120 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4370. Min Act: -0.1700
Data Index: 7493421 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4682. Min Act: -0.1700
Data Index: 6577559 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4682. Min Act: -0.1700
Data Index: 4428918 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4682. Min Act: -0.1700
Data Index: 4209506 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4370. Min Act: -0.1700
Data Index: 1748289 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4370. Min Act: -0.1700
Data Index: 5250219 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4057. Min Act: -0.1699
Data Index: 5647595 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4370. Min Act: -0.1700
Data Index: 4357674 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8745. Min Range: -4.8745
Max Act: 4.4370. Min Act: -0.1700
Data Index: 1560514 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19