Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4704 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0895. Min Range: -5.0895
Max Act: 5.0895. Min Act: -0.1700
Data Index: 3179010 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0895. Min Range: -5.0895
Max Act: 5.0270. Min Act: -0.1700
Data Index: 243247 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.9333. Min Act: -0.1700
Data Index: 7623184 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.8395. Min Act: -0.1700
Data Index: 5576761 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.8083. Min Act: -0.1700
Data Index: 449466 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.7458. Min Act: -0.1700
Data Index: 6114453 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.7458. Min Act: -0.1700
Data Index: 2048475 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.7145. Min Act: -0.1700
Data Index: 6261475 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.6833. Min Act: -0.1700
Data Index: 6695937 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.6833. Min Act: -0.1700
Data Index: 2385131 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.6520. Min Act: -0.1700
Data Index: 547790 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.6520. Min Act: -0.1700
Data Index: 82 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.5895. Min Act: -0.1700
Data Index: 8090249 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.5895. Min Act: -0.1700
Data Index: 4597714 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.5895. Min Act: -0.1700
Data Index: 2067864 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.5583. Min Act: -0.1700
Data Index: 631888 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.5583. Min Act: -0.1700
Data Index: 1003057 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.5583. Min Act: -0.1700
Data Index: 6314202 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.5270. Min Act: -0.1700
Data Index: 283198 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0895. Min Range: -5.0895
Max Act: 4.5895. Min Act: -0.1700
Data Index: 2525489 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19