Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6373 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.8738. Min Act: -0.1700
Data Index: 3867136 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.7800. Min Act: -0.1700
Data Index: 3235451 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.8113. Min Act: -0.1700
Data Index: 920928 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.7800. Min Act: -0.1700
Data Index: 267692 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.7644. Min Act: -0.1700
Data Index: 3481299 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.7331. Min Act: -0.1700
Data Index: 6604351 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.7175. Min Act: -0.1700
Data Index: 4016323 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.7175. Min Act: -0.1700
Data Index: 1511035 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6705. Min Act: -0.1700
Data Index: 8466002 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6549. Min Act: -0.1700
Data Index: 2221051 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6392. Min Act: -0.1700
Data Index: 5540648 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6392. Min Act: -0.1700
Data Index: 3820292 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6392. Min Act: -0.1700
Data Index: 2249656 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6392. Min Act: -0.1700
Data Index: 6317235 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6392. Min Act: -0.1700
Data Index: 4516122 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6236. Min Act: -0.1700
Data Index: 3652544 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6236. Min Act: -0.1700
Data Index: 2503403 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6236. Min Act: -0.1700
Data Index: 5753470 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6079. Min Act: -0.1700
Data Index: 6101873 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8738. Min Range: -3.8738
Max Act: 3.6079. Min Act: -0.1700
Data Index: 42768 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19