Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3152 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0579. Min Range: -7.0579
Max Act: 7.0579. Min Act: -0.1700
Data Index: 7509512 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.8079. Min Act: -0.1700
Data Index: 250699 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.7142. Min Act: -0.1700
Data Index: 4237756 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.6204. Min Act: -0.1700
Data Index: 3807720 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.5267. Min Act: -0.1700
Data Index: 7882172 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.5267. Min Act: -0.1700
Data Index: 6477195 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.4954. Min Act: -0.1700
Data Index: 396092 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.4954. Min Act: -0.1700
Data Index: 1542185 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.4329. Min Act: -0.1700
Data Index: 507965 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.4642. Min Act: -0.1700
Data Index: 2224940 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.4642. Min Act: -0.1700
Data Index: 4319454 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.4329. Min Act: -0.1700
Data Index: 810943 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.4329. Min Act: -0.1700
Data Index: 1693024 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.4017. Min Act: -0.1700
Data Index: 3259238 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.3704. Min Act: -0.1700
Data Index: 649686 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.4017. Min Act: -0.1700
Data Index: 3647376 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.4329. Min Act: -0.1700
Data Index: 867408 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.4017. Min Act: -0.1700
Data Index: 5331908 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.3704. Min Act: -0.1700
Data Index: 1041791 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0579. Min Range: -7.0579
Max Act: 6.3704. Min Act: -0.1700
Data Index: 3024806 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19