Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 627 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.6454. Min Act: -0.1700
Data Index: 992068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.5931. Min Act: -0.1700
Data Index: 8817365 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.5406. Min Act: -0.1700
Data Index: 2329590 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.5318. Min Act: -0.1692
Data Index: 3208653 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.5318. Min Act: -0.1694
Data Index: 838794 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.5318. Min Act: -0.1700
Data Index: 8560448 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.5143. Min Act: -0.1700
Data Index: 1436732 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.5143. Min Act: -0.1700
Data Index: 6395495 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.5143. Min Act: -0.1700
Data Index: 6832071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.5143. Min Act: -0.1700
Data Index: 7897006 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.5055. Min Act: -0.1700
Data Index: 6064237 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.4967. Min Act: -0.1700
Data Index: 7173151 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.4967. Min Act: -0.1700
Data Index: 5788280 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.4967. Min Act: -0.1700
Data Index: 3821073 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.4879. Min Act: -0.1700
Data Index: 4661513 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.4879. Min Act: -0.1700
Data Index: 2270761 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.4879. Min Act: -0.1700
Data Index: 3561087 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.4879. Min Act: -0.1700
Data Index: 1448247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.4879. Min Act: -0.1700
Data Index: 8272636 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6454. Min Range: -1.6454
Max Act: 1.4704. Min Act: -0.1700
Data Index: 598377 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19