Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9445. Min Act: -0.1700
Data Index: 6497058 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9287. Min Act: -0.1700
Data Index: 7289054 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8652. Min Act: -0.1700
Data Index: 3132226 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8493. Min Act: -0.1700
Data Index: 4256778 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7538. Min Act: -0.1700
Data Index: 7299341 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7538. Min Act: -0.1700
Data Index: 1507560 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7538. Min Act: -0.1700
Data Index: 7256503 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7378. Min Act: -0.1700
Data Index: 773387 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7218. Min Act: -0.1700
Data Index: 3144483 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7218. Min Act: -0.1700
Data Index: 4141117 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7059. Min Act: -0.1700
Data Index: 1075974 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.7218. Min Act: -0.1700
Data Index: 2895753 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.6899. Min Act: -0.1700
Data Index: 728679 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.6899. Min Act: -0.1700
Data Index: 3390447 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.6738. Min Act: -0.1700
Data Index: 8016449 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.6738. Min Act: -0.1700
Data Index: 7568143 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.6578. Min Act: -0.1700
Data Index: 4406686 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.6578. Min Act: -0.1700
Data Index: 7221173 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.6578. Min Act: -0.1700
Data Index: 6968345 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.6418. Min Act: -0.1700
Data Index: 4878203 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19