Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.8210. Min Act: -0.1700
Data Index: 8715686 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.8210. Min Act: -0.1700
Data Index: 1292681 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.8210. Min Act: -0.1700
Data Index: 3423666 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.7272. Min Act: -0.1700
Data Index: 3059170 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.6022. Min Act: -0.1700
Data Index: 7866854 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.6022. Min Act: -0.1700
Data Index: 3123592 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.5710. Min Act: -0.1700
Data Index: 6217602 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.5397. Min Act: -0.1700
Data Index: 7856916 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.5397. Min Act: -0.1700
Data Index: 5599093 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.5085. Min Act: -0.1700
Data Index: 1075887 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.5085. Min Act: -0.1700
Data Index: 1438546 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.5085. Min Act: -0.1700
Data Index: 4587443 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.5085. Min Act: -0.1700
Data Index: 6811429 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.5085. Min Act: -0.1700
Data Index: 7976441 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.4772. Min Act: -0.1700
Data Index: 654567 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.4772. Min Act: -0.1700
Data Index: 5546167 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.4460. Min Act: -0.1700
Data Index: 6073756 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.4460. Min Act: -0.1700
Data Index: 2141772 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.4460. Min Act: -0.1700
Data Index: 4891328 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8210. Min Range: -5.8210
Max Act: 5.4772. Min Act: -0.1700
Data Index: 5290291 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19