Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4292. Min Range: -9.4292
Max Act: 9.4292. Min Act: -0.1700
Data Index: 3601840 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4292. Min Range: -9.4292
Max Act: 9.3042. Min Act: -0.1700
Data Index: 5119929 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4292. Min Range: -9.4292
Max Act: 9.1792. Min Act: -0.1700
Data Index: 2492724 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4292. Min Range: -9.4292
Max Act: 9.1792. Min Act: -0.1700
Data Index: 5216821 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4292. Min Range: -9.4292
Max Act: 9.0542. Min Act: -0.1700
Data Index: 2660310 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.9917. Min Act: -0.1700
Data Index: 1707997 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.9917. Min Act: -0.1700
Data Index: 600347 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.9917. Min Act: -0.1700
Data Index: 6101326 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.9292. Min Act: -0.1700
Data Index: 3622556 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.9292. Min Act: -0.1700
Data Index: 3815704 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.8667. Min Act: -0.1700
Data Index: 6360147 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.8667. Min Act: -0.1700
Data Index: 3972597 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.8042. Min Act: -0.1700
Data Index: 7884892 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.7417. Min Act: -0.1700
Data Index: 8133232 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.7417. Min Act: -0.1700
Data Index: 698620 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.7417. Min Act: -0.1700
Data Index: 706205 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.7417. Min Act: -0.1700
Data Index: 8619361 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.7417. Min Act: -0.1700
Data Index: 5657563 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.7417. Min Act: -0.1700
Data Index: 7059350 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4292. Min Range: -9.4292
Max Act: 8.7417. Min Act: -0.1700
Data Index: 7218782 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19