Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2512 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.4975. Min Act: -0.1700
Data Index: 4539317 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.3412. Min Act: -0.1700
Data Index: 1477065 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.2787. Min Act: -0.1700
Data Index: 5583551 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.1850. Min Act: -0.1700
Data Index: 902885 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.1225. Min Act: -0.1700
Data Index: 306289 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.1225. Min Act: -0.1700
Data Index: 4957331 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.1225. Min Act: -0.1700
Data Index: 1538716 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.1225. Min Act: -0.1700
Data Index: 6401327 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.1537. Min Act: -0.1700
Data Index: 7089020 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.0912. Min Act: -0.1700
Data Index: 3200224 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.0287. Min Act: -0.1700
Data Index: 4183329 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.0287. Min Act: -0.1700
Data Index: 3782609 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.0287. Min Act: -0.1700
Data Index: 7342823 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.0287. Min Act: -0.1700
Data Index: 33426 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4975. Min Range: -5.4975
Max Act: 5.0600. Min Act: -0.1700
Data Index: 8339104 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4975. Min Range: -5.4975
Max Act: 4.9975. Min Act: -0.1700
Data Index: 3558738 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4975. Min Range: -5.4975
Max Act: 4.9975. Min Act: -0.1700
Data Index: 5098206 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4975. Min Range: -5.4975
Max Act: 4.9975. Min Act: -0.1700
Data Index: 2621777 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4975. Min Range: -5.4975
Max Act: 4.9975. Min Act: -0.1700
Data Index: 3365827 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4975. Min Range: -5.4975
Max Act: 4.9975. Min Act: -0.1700
Data Index: 7696970 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19