Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1202 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.5517. Min Act: -0.1700
Data Index: 1491055 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.5517. Min Act: -0.1700
Data Index: 7574409 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.5204. Min Act: -0.1700
Data Index: 6494487 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4892. Min Act: -0.1700
Data Index: 2690299 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4892. Min Act: -0.1700
Data Index: 4738022 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4579. Min Act: -0.1700
Data Index: 5634816 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4579. Min Act: -0.1700
Data Index: 1269807 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3954. Min Act: -0.1700
Data Index: 4491269 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3954. Min Act: -0.1700
Data Index: 2103245 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4267. Min Act: -0.1700
Data Index: 7384190 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3954. Min Act: -0.1700
Data Index: 3197486 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3954. Min Act: -0.1700
Data Index: 8659997 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3954. Min Act: -0.1700
Data Index: 6144018 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3954. Min Act: -0.1700
Data Index: 1187772 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3642. Min Act: -0.1700
Data Index: 8784 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3642. Min Act: -0.1700
Data Index: 4088391 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3642. Min Act: -0.1700
Data Index: 3906310 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3329. Min Act: -0.1700
Data Index: 3066994 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3329. Min Act: -0.1700
Data Index: 4182705 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3642. Min Act: -0.1700
Data Index: 3915271 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19