Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3043 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.8238. Min Act: -0.1700
Data Index: 4139715 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.6363. Min Act: -0.1700
Data Index: 7732444 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.5738. Min Act: -0.1700
Data Index: 6677627 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.5738. Min Act: -0.1700
Data Index: 6223649 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.4488. Min Act: -0.1700
Data Index: 3822401 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.4488. Min Act: -0.1700
Data Index: 7298211 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.3238. Min Act: -0.1700
Data Index: 4022405 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.3238. Min Act: -0.1700
Data Index: 2579682 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.2613. Min Act: -0.1700
Data Index: 7292382 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.2613. Min Act: -0.1700
Data Index: 2178433 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.2613. Min Act: -0.1700
Data Index: 91673 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.2613. Min Act: -0.1700
Data Index: 6197485 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.1988. Min Act: -0.1700
Data Index: 8747004 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.1988. Min Act: -0.1699
Data Index: 4580960 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.1988. Min Act: -0.1700
Data Index: 2954308 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.1363. Min Act: -0.1700
Data Index: 1213563 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.1988. Min Act: -0.1700
Data Index: 5262251 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.1363. Min Act: -0.1700
Data Index: 5259563 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.1988. Min Act: -0.1659
Data Index: 100374 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8238. Min Range: -10.8238
Max Act: 10.1988. Min Act: -0.1700
Data Index: 2311428 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19