Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1084 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.4625. Min Act: -0.1700
Data Index: 5132116 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.3319. Min Act: -0.1700
Data Index: 422938 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2990. Min Act: -0.1700
Data Index: 3705578 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2825. Min Act: -0.1700
Data Index: 1060903 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2661. Min Act: -0.1700
Data Index: 853437 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2495. Min Act: -0.1700
Data Index: 44339 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2330. Min Act: -0.1700
Data Index: 4487269 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2330. Min Act: -0.1700
Data Index: 1796599 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2330. Min Act: -0.1700
Data Index: 5603034 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2165. Min Act: -0.1700
Data Index: 7959446 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2330. Min Act: -0.1700
Data Index: 1601438 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2330. Min Act: -0.1700
Data Index: 1236934 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.1999. Min Act: -0.1700
Data Index: 2728207 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2165. Min Act: -0.1700
Data Index: 3702897 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2330. Min Act: -0.1700
Data Index: 7131942 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.1999. Min Act: -0.1699
Data Index: 1963087 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.1999. Min Act: -0.1700
Data Index: 5870086 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.1833. Min Act: -0.1700
Data Index: 2328499 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.1999. Min Act: -0.1700
Data Index: 1220533 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4625. Min Range: -2.4625
Max Act: 2.2165. Min Act: -0.1700
Data Index: 2541359 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19