Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4678 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.9470. Min Act: -0.1700
Data Index: 2321809 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.7282. Min Act: -0.1700
Data Index: 1561743 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.4470. Min Act: -0.1700
Data Index: 8240282 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.4782. Min Act: -0.1700
Data Index: 1561758 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.4157. Min Act: -0.1700
Data Index: 605987 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.3532. Min Act: -0.1700
Data Index: 3778020 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.2595. Min Act: -0.1700
Data Index: 1831380 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.2595. Min Act: -0.1700
Data Index: 3778019 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.2282. Min Act: -0.1700
Data Index: 6127405 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.2282. Min Act: -0.1700
Data Index: 1017551 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.2282. Min Act: -0.1700
Data Index: 7451957 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.1345. Min Act: -0.1700
Data Index: 7012652 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.1657. Min Act: -0.1700
Data Index: 5314900 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.1657. Min Act: -0.1700
Data Index: 2985637 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.1032. Min Act: -0.1700
Data Index: 5928147 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.1345. Min Act: -0.1700
Data Index: 1293158 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.1032. Min Act: -0.1700
Data Index: 6588070 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.0720. Min Act: -0.1700
Data Index: 2250728 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.0407. Min Act: -0.1700
Data Index: 2374620 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.0407. Min Act: -0.1700
Data Index: 6586699 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19