Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4199 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3463. Min Range: -8.3463
Max Act: 8.3463. Min Act: -0.1700
Data Index: 807628 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.9713. Min Act: -0.1700
Data Index: 4180426 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.8463. Min Act: -0.1700
Data Index: 188489 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.8463. Min Act: -0.1700
Data Index: 1550472 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.7838. Min Act: -0.1700
Data Index: 2916253 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.7838. Min Act: -0.1700
Data Index: 7684243 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.7525. Min Act: -0.1700
Data Index: 2130491 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.7525. Min Act: -0.1700
Data Index: 7671231 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.7838. Min Act: -0.1700
Data Index: 8172710 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.7838. Min Act: -0.1700
Data Index: 2456508 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.7525. Min Act: -0.1700
Data Index: 3984407 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.6900. Min Act: -0.1700
Data Index: 7105744 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.6588. Min Act: -0.1700
Data Index: 3776789 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.6588. Min Act: -0.1700
Data Index: 408026 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.6275. Min Act: -0.1700
Data Index: 4934344 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.5963. Min Act: -0.1700
Data Index: 1683432 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.5963. Min Act: -0.1700
Data Index: 3558606 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.5963. Min Act: -0.1700
Data Index: 1936907 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.5963. Min Act: -0.1700
Data Index: 5149257 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3463. Min Range: -8.3463
Max Act: 7.5650. Min Act: -0.1700
Data Index: 1161367 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19