Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5077 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8736. Min Range: -7.8736
Max Act: 7.8736. Min Act: -0.1700
Data Index: 4221864 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8736. Min Range: -7.8736
Max Act: 7.4049. Min Act: -0.1700
Data Index: 7361931 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8736. Min Range: -7.8736
Max Act: 7.1861. Min Act: -0.1700
Data Index: 8334968 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8736. Min Range: -7.8736
Max Act: 7.0924. Min Act: -0.1700
Data Index: 8711116 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.9674. Min Act: -0.1700
Data Index: 4690969 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.9361. Min Act: -0.1700
Data Index: 7662295 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.9361. Min Act: -0.1700
Data Index: 1504585 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.9049. Min Act: -0.1700
Data Index: 2815470 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.9361. Min Act: -0.1700
Data Index: 83486 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.9049. Min Act: -0.1700
Data Index: 6810457 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.8736. Min Act: -0.1700
Data Index: 3519986 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.8736. Min Act: -0.1700
Data Index: 5148822 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.8424. Min Act: -0.1700
Data Index: 5077100 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.8424. Min Act: -0.1700
Data Index: 5662872 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.7486. Min Act: -0.1700
Data Index: 5806514 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.7799. Min Act: -0.1700
Data Index: 2653399 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.7799. Min Act: -0.1700
Data Index: 5780635 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.7486. Min Act: -0.1700
Data Index: 6568814 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.8111. Min Act: -0.1700
Data Index: 5377497 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8736. Min Range: -7.8736
Max Act: 6.7486. Min Act: -0.1700
Data Index: 7770648 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19