Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5660 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1662. Min Range: -4.1662
Max Act: 4.1662. Min Act: -0.1700
Data Index: 4007004 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1662. Min Range: -4.1662
Max Act: 4.1349. Min Act: -0.1700
Data Index: 3213308 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1662. Min Range: -4.1662
Max Act: 4.0724. Min Act: -0.1700
Data Index: 2327091 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1662. Min Range: -4.1662
Max Act: 4.0724. Min Act: -0.1700
Data Index: 7414041 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1662. Min Range: -4.1662
Max Act: 4.0099. Min Act: -0.1700
Data Index: 4221953 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1662. Min Range: -4.1662
Max Act: 4.0411. Min Act: -0.1700
Data Index: 2069627 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1662. Min Range: -4.1662
Max Act: 4.0411. Min Act: -0.1700
Data Index: 2492724 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1662. Min Range: -4.1662
Max Act: 4.0411. Min Act: -0.1700
Data Index: 8774354 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1662. Min Range: -4.1662
Max Act: 4.0411. Min Act: -0.1700
Data Index: 7828184 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1662. Min Range: -4.1662
Max Act: 3.9786. Min Act: -0.1700
Data Index: 563330 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1662. Min Range: -4.1662
Max Act: 3.9786. Min Act: -0.1700
Data Index: 614095 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1662. Min Range: -4.1662
Max Act: 3.9786. Min Act: -0.1700
Data Index: 6492773 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1662. Min Range: -4.1662
Max Act: 3.9786. Min Act: -0.1700
Data Index: 7694321 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1662. Min Range: -4.1662
Max Act: 3.9473. Min Act: -0.1700
Data Index: 7354283 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1662. Min Range: -4.1662
Max Act: 3.9473. Min Act: -0.1700
Data Index: 1839321 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1662. Min Range: -4.1662
Max Act: 3.9473. Min Act: -0.1700
Data Index: 7896918 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1662. Min Range: -4.1662
Max Act: 3.9473. Min Act: -0.1700
Data Index: 5434795 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1662. Min Range: -4.1662
Max Act: 3.9786. Min Act: -0.1700
Data Index: 6745308 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1662. Min Range: -4.1662
Max Act: 3.9473. Min Act: -0.1700
Data Index: 3136828 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1662. Min Range: -4.1662
Max Act: 3.9473. Min Act: -0.1700
Data Index: 2004565 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19