Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.2502. Min Act: -0.1700
Data Index: 3780165 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0627. Min Act: -0.1700
Data Index: 2392228 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0002. Min Act: -0.1700
Data Index: 7975020 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9690. Min Act: -0.1700
Data Index: 3435473 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9690. Min Act: -0.1700
Data Index: 5309539 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9377. Min Act: -0.1700
Data Index: 4872101 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9377. Min Act: -0.1700
Data Index: 5247725 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9065. Min Act: -0.1700
Data Index: 765661 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9065. Min Act: -0.1700
Data Index: 3327169 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9065. Min Act: -0.1700
Data Index: 8291183 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9065. Min Act: -0.1700
Data Index: 3927693 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.8440. Min Act: -0.1700
Data Index: 910114 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.8440. Min Act: -0.1700
Data Index: 3703619 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.8440. Min Act: -0.1700
Data Index: 7761043 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.8440. Min Act: -0.1700
Data Index: 4863061 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.8127. Min Act: -0.1700
Data Index: 8635187 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.8127. Min Act: -0.1700
Data Index: 5441224 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.8127. Min Act: -0.1700
Data Index: 2677331 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.7815. Min Act: -0.1700
Data Index: 1775203 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.7815. Min Act: -0.1700
Data Index: 329889 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19