Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4269 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2986. Min Range: -7.2986
Max Act: 7.2986. Min Act: -0.1700
Data Index: 5359479 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2986. Min Range: -7.2986
Max Act: 7.1423. Min Act: -0.1700
Data Index: 6097391 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2986. Min Range: -7.2986
Max Act: 7.1423. Min Act: -0.1700
Data Index: 169044 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2986. Min Range: -7.2986
Max Act: 7.0798. Min Act: -0.1700
Data Index: 3942635 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.9861. Min Act: -0.1700
Data Index: 5683565 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.9861. Min Act: -0.1700
Data Index: 8186319 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.9548. Min Act: -0.1700
Data Index: 5675249 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.9236. Min Act: -0.1700
Data Index: 4403380 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.9236. Min Act: -0.1700
Data Index: 6716290 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.8923. Min Act: -0.1700
Data Index: 7077714 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.8298. Min Act: -0.1700
Data Index: 8207357 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.8923. Min Act: -0.1700
Data Index: 5882382 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.8611. Min Act: -0.1700
Data Index: 6975257 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.8298. Min Act: -0.1700
Data Index: 922892 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.8298. Min Act: -0.1700
Data Index: 6755524 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.8611. Min Act: -0.1700
Data Index: 5204691 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.7673. Min Act: -0.1700
Data Index: 1399022 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.7986. Min Act: -0.1700
Data Index: 2053452 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.8298. Min Act: -0.1700
Data Index: 6390679 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2986. Min Range: -7.2986
Max Act: 6.7673. Min Act: -0.1700
Data Index: 6874857 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19