Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1005 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.6971. Min Act: -0.1700
Data Index: 8301859 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.6033. Min Act: -0.1700
Data Index: 5392646 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.5721. Min Act: -0.1700
Data Index: 2724381 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.5408. Min Act: -0.1700
Data Index: 1967102 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.4471. Min Act: -0.1700
Data Index: 7097883 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.4471. Min Act: -0.1700
Data Index: 89578 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.4471. Min Act: -0.1700
Data Index: 8619308 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.4158. Min Act: -0.1700
Data Index: 3311176 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.4158. Min Act: -0.1700
Data Index: 831128 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.3221. Min Act: -0.1700
Data Index: 6245805 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.3846. Min Act: -0.1700
Data Index: 7635502 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.3533. Min Act: -0.1700
Data Index: 23812 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.3221. Min Act: -0.1700
Data Index: 7793664 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.3221. Min Act: -0.1700
Data Index: 6786648 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.2908. Min Act: -0.1700
Data Index: 6657757 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.2908. Min Act: -0.1700
Data Index: 5539051 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.2596. Min Act: -0.1700
Data Index: 3873176 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.2596. Min Act: -0.1700
Data Index: 4119553 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.2596. Min Act: -0.1700
Data Index: 7652374 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6971. Min Range: -5.6971
Max Act: 5.2283. Min Act: -0.1700
Data Index: 4744429 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19