Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 673 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4118. Min Range: -8.4118
Max Act: 8.4118. Min Act: -0.1700
Data Index: 6051632 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4118. Min Range: -8.4118
Max Act: 8.3493. Min Act: -0.1700
Data Index: 4557231 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4118. Min Range: -8.4118
Max Act: 8.0368. Min Act: -0.1700
Data Index: 7635909 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.9743. Min Act: -0.1700
Data Index: 7054408 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.9743. Min Act: -0.1700
Data Index: 233670 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.8493. Min Act: -0.1700
Data Index: 5711667 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.7868. Min Act: -0.1700
Data Index: 2181752 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.7243. Min Act: -0.1700
Data Index: 6771446 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.7243. Min Act: -0.1700
Data Index: 5690210 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.7243. Min Act: -0.1700
Data Index: 8504196 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.7243. Min Act: -0.1700
Data Index: 7393845 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.7243. Min Act: -0.1700
Data Index: 4775344 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.7243. Min Act: -0.1700
Data Index: 7003983 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.7243. Min Act: -0.1700
Data Index: 1187233 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.6618. Min Act: -0.1700
Data Index: 4893476 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.6618. Min Act: -0.1700
Data Index: 5970434 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.6618. Min Act: -0.1700
Data Index: 3488018 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.6618. Min Act: -0.1700
Data Index: 190318 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.6618. Min Act: -0.1700
Data Index: 256473 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4118. Min Range: -8.4118
Max Act: 7.6618. Min Act: -0.1700
Data Index: 304641 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19