Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5142. Min Range: -7.5142
Max Act: 7.5142. Min Act: -0.1700
Data Index: 1779238 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5142. Min Range: -7.5142
Max Act: 7.2329. Min Act: -0.1700
Data Index: 6851166 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5142. Min Range: -7.5142
Max Act: 7.0767. Min Act: -0.1700
Data Index: 3509849 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5142. Min Range: -7.5142
Max Act: 7.0454. Min Act: -0.1700
Data Index: 5086661 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.9204. Min Act: -0.1700
Data Index: 5852438 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.8892. Min Act: -0.1700
Data Index: 485664 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.8579. Min Act: -0.1700
Data Index: 7983646 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.8579. Min Act: -0.1700
Data Index: 5610738 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.8267. Min Act: -0.1700
Data Index: 5320871 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.7642. Min Act: -0.1700
Data Index: 3072525 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.7642. Min Act: -0.1700
Data Index: 3148760 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.7642. Min Act: -0.1700
Data Index: 779511 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.7017. Min Act: -0.1700
Data Index: 4346026 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.6704. Min Act: -0.1700
Data Index: 8289205 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.6704. Min Act: -0.1700
Data Index: 1815791 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.6704. Min Act: -0.1700
Data Index: 243219 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.6392. Min Act: -0.1700
Data Index: 7853045 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.6079. Min Act: -0.1700
Data Index: 5927936 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.6704. Min Act: -0.1700
Data Index: 7379337 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5142. Min Range: -7.5142
Max Act: 6.6392. Min Act: -0.1700
Data Index: 3820770 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19