Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 93 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.9081. Min Act: -0.1700
Data Index: 586267 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.9081. Min Act: -0.1700
Data Index: 7321015 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.8768. Min Act: -0.1700
Data Index: 7174200 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.8299. Min Act: -0.1700
Data Index: 4808531 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.8299. Min Act: -0.1700
Data Index: 1668288 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.8143. Min Act: -0.1700
Data Index: 8125997 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.7986. Min Act: -0.1700
Data Index: 8096976 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.7986. Min Act: -0.1700
Data Index: 1311443 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.7830. Min Act: -0.1700
Data Index: 7433881 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.7361. Min Act: -0.1700
Data Index: 150047 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.7517. Min Act: -0.1700
Data Index: 1975116 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.7517. Min Act: -0.1700
Data Index: 6255829 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.7204. Min Act: -0.1700
Data Index: 7454283 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.7361. Min Act: -0.1700
Data Index: 1471521 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.7204. Min Act: -0.1700
Data Index: 8830916 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.7361. Min Act: -0.1700
Data Index: 8211599 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.6892. Min Act: -0.1700
Data Index: 5639482 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.6892. Min Act: -0.1700
Data Index: 3814927 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.6735. Min Act: -0.1700
Data Index: 2029743 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9081. Min Range: -3.9081
Max Act: 3.6735. Min Act: -0.1700
Data Index: 7334777 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19