Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0397. Min Range: -5.0397
Max Act: 5.0397. Min Act: -0.1700
Data Index: 3404938 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.9772. Min Act: -0.1700
Data Index: 3404932 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.9460. Min Act: -0.1700
Data Index: 671235 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.9147. Min Act: -0.1700
Data Index: 1849113 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.8835. Min Act: -0.1700
Data Index: 549652 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.8522. Min Act: -0.1700
Data Index: 1609187 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.8522. Min Act: -0.1700
Data Index: 8532702 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.8522. Min Act: -0.1700
Data Index: 4462241 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.8210. Min Act: -0.1700
Data Index: 3404937 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.7272. Min Act: -0.1700
Data Index: 3404931 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.7585. Min Act: -0.1700
Data Index: 6297136 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.7585. Min Act: -0.1700
Data Index: 6671784 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.7272. Min Act: -0.1700
Data Index: 6143939 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.6960. Min Act: -0.1700
Data Index: 8532694 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.6960. Min Act: -0.1700
Data Index: 8532704 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.6960. Min Act: -0.1700
Data Index: 3222765 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.6647. Min Act: -0.1700
Data Index: 6484409 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.6647. Min Act: -0.1700
Data Index: 5608163 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.6647. Min Act: -0.1700
Data Index: 5598798 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0397. Min Range: -5.0397
Max Act: 4.6647. Min Act: -0.1700
Data Index: 8532695 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19