Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6276 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.9448. Min Act: -0.1700
Data Index: 3745102 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.6011. Min Act: -0.1700
Data Index: 6163682 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.5698. Min Act: -0.1700
Data Index: 4517829 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.5386. Min Act: -0.1700
Data Index: 7171678 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.4448. Min Act: -0.1700
Data Index: 988168 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.4136. Min Act: -0.1700
Data Index: 4123479 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.2886. Min Act: -0.1700
Data Index: 3603761 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.3198. Min Act: -0.1700
Data Index: 3211788 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.2261. Min Act: -0.1700
Data Index: 3677416 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.2261. Min Act: -0.1700
Data Index: 4698415 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.2573. Min Act: -0.1700
Data Index: 7362290 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.1948. Min Act: -0.1700
Data Index: 4246116 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.1948. Min Act: -0.1700
Data Index: 3653188 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.1948. Min Act: -0.1700
Data Index: 4508877 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.1948. Min Act: -0.1700
Data Index: 5969509 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.1636. Min Act: -0.1700
Data Index: 4436018 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.1323. Min Act: -0.1700
Data Index: 5300708 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.1636. Min Act: -0.1700
Data Index: 5572891 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.1323. Min Act: -0.1700
Data Index: 336851 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9448. Min Range: -5.9448
Max Act: 5.1323. Min Act: -0.1700
Data Index: 5356578 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19