Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.6659. Min Act: -0.1700
Data Index: 4645857 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.5721. Min Act: -0.1700
Data Index: 6036781 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.5721. Min Act: -0.1700
Data Index: 8617312 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.5409. Min Act: -0.1700
Data Index: 530968 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.5409. Min Act: -0.1700
Data Index: 665001 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.5409. Min Act: -0.1700
Data Index: 7047814 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.5409. Min Act: -0.1700
Data Index: 2038573 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.5096. Min Act: -0.1700
Data Index: 3535692 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.5409. Min Act: -0.1700
Data Index: 4864667 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.5096. Min Act: -0.1700
Data Index: 2585410 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.4784. Min Act: -0.1700
Data Index: 3137276 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.4784. Min Act: -0.1700
Data Index: 4438046 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.4784. Min Act: -0.1700
Data Index: 722846 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.4471. Min Act: -0.1700
Data Index: 6627615 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.4471. Min Act: -0.1700
Data Index: 333685 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.4471. Min Act: -0.1700
Data Index: 929207 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.4471. Min Act: -0.1700
Data Index: 5652452 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.4471. Min Act: -0.1700
Data Index: 5227605 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.4471. Min Act: -0.1700
Data Index: 900849 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6659. Min Range: -6.6659
Max Act: 6.4471. Min Act: -0.1700
Data Index: 4957290 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19