Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3069 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.3741. Min Act: -0.1700
Data Index: 1608868 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.3116. Min Act: -0.1700
Data Index: 7802569 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.2178. Min Act: -0.1700
Data Index: 1211650 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.1553. Min Act: -0.1700
Data Index: 4227355 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.1553. Min Act: -0.1700
Data Index: 2387559 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.1553. Min Act: -0.1700
Data Index: 3422050 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.1553. Min Act: -0.1700
Data Index: 991794 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.1553. Min Act: -0.1700
Data Index: 1107344 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.1553. Min Act: -0.1700
Data Index: 7221465 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.1553. Min Act: -0.1700
Data Index: 7769171 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.1553. Min Act: -0.1700
Data Index: 7283764 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.1241. Min Act: -0.1700
Data Index: 6283194 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.0928. Min Act: -0.1700
Data Index: 2501692 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.0928. Min Act: -0.1700
Data Index: 2559426 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.0928. Min Act: -0.1700
Data Index: 2789772 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.0928. Min Act: -0.1700
Data Index: 3782742 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.1241. Min Act: -0.1700
Data Index: 8413748 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.0616. Min Act: -0.1700
Data Index: 6411627 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.0928. Min Act: -0.1700
Data Index: 5252540 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3741. Min Range: -4.3741
Max Act: 4.0616. Min Act: -0.1700
Data Index: 30260 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19