Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 497 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5040. Min Range: -7.5040
Max Act: 7.5040. Min Act: -0.1700
Data Index: 4960179 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5040. Min Range: -7.5040
Max Act: 7.2852. Min Act: -0.1700
Data Index: 290896 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5040. Min Range: -7.5040
Max Act: 7.1290. Min Act: -0.1700
Data Index: 1507924 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5040. Min Range: -7.5040
Max Act: 7.1290. Min Act: -0.1700
Data Index: 7345286 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5040. Min Range: -7.5040
Max Act: 7.0977. Min Act: -0.1700
Data Index: 623264 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5040. Min Range: -7.5040
Max Act: 7.0977. Min Act: -0.1700
Data Index: 8077810 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5040. Min Range: -7.5040
Max Act: 7.0665. Min Act: -0.1700
Data Index: 1641893 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5040. Min Range: -7.5040
Max Act: 7.0665. Min Act: -0.1700
Data Index: 4561774 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5040. Min Range: -7.5040
Max Act: 7.0352. Min Act: -0.1700
Data Index: 7132132 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5040. Min Range: -7.5040
Max Act: 6.8790. Min Act: -0.1700
Data Index: 7437687 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5040. Min Range: -7.5040
Max Act: 6.8790. Min Act: -0.1700
Data Index: 1481716 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5040. Min Range: -7.5040
Max Act: 6.8477. Min Act: -0.1700
Data Index: 7954016 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5040. Min Range: -7.5040
Max Act: 6.8477. Min Act: -0.1700
Data Index: 8038592 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5040. Min Range: -7.5040
Max Act: 6.8165. Min Act: -0.1700
Data Index: 8645952 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5040. Min Range: -7.5040
Max Act: 6.7852. Min Act: -0.1700
Data Index: 1605809 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5040. Min Range: -7.5040
Max Act: 6.7852. Min Act: -0.1700
Data Index: 1897955 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5040. Min Range: -7.5040
Max Act: 6.7852. Min Act: -0.1700
Data Index: 7826264 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5040. Min Range: -7.5040
Max Act: 6.7852. Min Act: -0.1700
Data Index: 3553383 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5040. Min Range: -7.5040
Max Act: 6.7227. Min Act: -0.1700
Data Index: 6181328 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5040. Min Range: -7.5040
Max Act: 6.6915. Min Act: -0.1700
Data Index: 7878360 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19