Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5319 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5878. Min Range: -9.5878
Max Act: 9.5878. Min Act: -0.1700
Data Index: 3140856 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5878. Min Range: -9.5878
Max Act: 9.1503. Min Act: -0.1700
Data Index: 382911 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5878. Min Range: -9.5878
Max Act: 9.0878. Min Act: -0.1700
Data Index: 1026120 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.9628. Min Act: -0.1700
Data Index: 4817401 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.9003. Min Act: -0.1700
Data Index: 4584934 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.7128. Min Act: -0.1700
Data Index: 6609816 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.7128. Min Act: -0.1700
Data Index: 6888313 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.7128. Min Act: -0.1700
Data Index: 5111965 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.7128. Min Act: -0.1700
Data Index: 7182899 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.6503. Min Act: -0.1700
Data Index: 4661453 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.5878. Min Act: -0.1700
Data Index: 3832320 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.6503. Min Act: -0.1700
Data Index: 1767216 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.6503. Min Act: -0.1700
Data Index: 285459 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.5878. Min Act: -0.1700
Data Index: 1829125 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.4628. Min Act: -0.1700
Data Index: 2532311 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.5253. Min Act: -0.1700
Data Index: 4999444 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.5253. Min Act: -0.1700
Data Index: 8766192 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.5253. Min Act: -0.1700
Data Index: 1525257 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.4628. Min Act: -0.1700
Data Index: 7299844 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5878. Min Range: -9.5878
Max Act: 8.4628. Min Act: -0.1700
Data Index: 7974788 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19