Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 95 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.3620. Min Act: -0.1700
Data Index: 7620974 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.3620. Min Act: -0.1700
Data Index: 2733895 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.3620. Min Act: -0.1700
Data Index: 6886084 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.3620. Min Act: -0.1700
Data Index: 3423318 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.3307. Min Act: -0.1700
Data Index: 5346900 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.3307. Min Act: -0.1700
Data Index: 4664178 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2995. Min Act: -0.1700
Data Index: 5620130 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2995. Min Act: -0.1700
Data Index: 7861405 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2682. Min Act: -0.1700
Data Index: 1853524 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2682. Min Act: -0.1700
Data Index: 2632747 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2369. Min Act: -0.1700
Data Index: 7214963 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2369. Min Act: -0.1700
Data Index: 1431969 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2682. Min Act: -0.1700
Data Index: 5169616 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2369. Min Act: -0.1700
Data Index: 3842914 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2057. Min Act: -0.1700
Data Index: 4654227 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2057. Min Act: -0.1700
Data Index: 583470 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2369. Min Act: -0.1700
Data Index: 5740421 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2057. Min Act: -0.1700
Data Index: 3797678 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2057. Min Act: -0.1700
Data Index: 4775055 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3620. Min Range: -4.3620
Max Act: 4.2057. Min Act: -0.1700
Data Index: 5090285 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19