Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3717 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1490. Min Range: -6.1490
Max Act: 6.1490. Min Act: -0.1700
Data Index: 145730 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.9303. Min Act: -0.1700
Data Index: 4599884 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.8053. Min Act: -0.1700
Data Index: 8686000 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.7428. Min Act: -0.1700
Data Index: 535350 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.7115. Min Act: -0.1700
Data Index: 2055968 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.7115. Min Act: -0.1700
Data Index: 3442217 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.7428. Min Act: -0.1700
Data Index: 6221291 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.6803. Min Act: -0.1700
Data Index: 2292970 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.6490. Min Act: -0.1700
Data Index: 7241944 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.6178. Min Act: -0.1700
Data Index: 4515278 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.5865. Min Act: -0.1700
Data Index: 1924820 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.5865. Min Act: -0.1700
Data Index: 4424632 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.5553. Min Act: -0.1700
Data Index: 8298856 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.5553. Min Act: -0.1700
Data Index: 1452192 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.5553. Min Act: -0.1700
Data Index: 1452178 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.5553. Min Act: -0.1700
Data Index: 2371208 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.5553. Min Act: -0.1700
Data Index: 3271747 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.5553. Min Act: -0.1700
Data Index: 4421593 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.5865. Min Act: -0.1700
Data Index: 1036642 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1490. Min Range: -6.1490
Max Act: 5.5553. Min Act: -0.1700
Data Index: 1888922 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19