Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.4744. Min Act: -0.1700
Data Index: 2042637 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.4119. Min Act: -0.1700
Data Index: 3070737 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.3806. Min Act: -0.1700
Data Index: 3058817 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.4431. Min Act: -0.1700
Data Index: 7968015 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.3806. Min Act: -0.1700
Data Index: 3919238 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.3494. Min Act: -0.1700
Data Index: 6289591 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.2556. Min Act: -0.1700
Data Index: 5570867 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.3181. Min Act: -0.1700
Data Index: 8367865 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.2556. Min Act: -0.1700
Data Index: 937341 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.2869. Min Act: -0.1700
Data Index: 849652 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.2556. Min Act: -0.1700
Data Index: 5959496 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.2244. Min Act: -0.1700
Data Index: 2813163 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.2244. Min Act: -0.1700
Data Index: 4864213 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.1931. Min Act: -0.1700
Data Index: 6255522 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.1619. Min Act: -0.1700
Data Index: 3119631 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.1931. Min Act: -0.1700
Data Index: 2910615 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.2244. Min Act: -0.1700
Data Index: 3900075 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.2244. Min Act: -0.1700
Data Index: 2356698 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.1619. Min Act: -0.1700
Data Index: 274744 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4744. Min Range: -4.4744
Max Act: 4.1306. Min Act: -0.1700
Data Index: 3772101 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19