Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2360. Min Range: -6.2360
Max Act: 6.2360. Min Act: -0.1700
Data Index: 5226382 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2360. Min Range: -6.2360
Max Act: 6.1735. Min Act: -0.1700
Data Index: 4224453 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2360. Min Range: -6.2360
Max Act: 6.0798. Min Act: -0.1700
Data Index: 4857561 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2360. Min Range: -6.2360
Max Act: 6.0485. Min Act: -0.1700
Data Index: 8285801 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2360. Min Range: -6.2360
Max Act: 6.0173. Min Act: -0.1700
Data Index: 145292 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.9860. Min Act: -0.1700
Data Index: 8773656 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2360. Min Range: -6.2360
Max Act: 6.0173. Min Act: -0.1700
Data Index: 8148510 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.9860. Min Act: -0.1700
Data Index: 2355405 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.9860. Min Act: -0.1700
Data Index: 7867610 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.9235. Min Act: -0.1700
Data Index: 8375236 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.9235. Min Act: -0.1700
Data Index: 2197411 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.9235. Min Act: -0.1700
Data Index: 5530338 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.8923. Min Act: -0.1700
Data Index: 4931239 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.8610. Min Act: -0.1700
Data Index: 5917268 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.8610. Min Act: -0.1700
Data Index: 6486633 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.8298. Min Act: -0.1700
Data Index: 5833970 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.8298. Min Act: -0.1700
Data Index: 4351365 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.8298. Min Act: -0.1700
Data Index: 1207802 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.8298. Min Act: -0.1700
Data Index: 3648312 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2360. Min Range: -6.2360
Max Act: 5.8298. Min Act: -0.1700
Data Index: 2102380 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19