Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6383 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0522. Min Range: -4.0522
Max Act: 4.0522. Min Act: -0.1700
Data Index: 8582082 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0522. Min Range: -4.0522
Max Act: 4.0522. Min Act: -0.1700
Data Index: 6606308 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.9897. Min Act: -0.1700
Data Index: 35947 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.9897. Min Act: -0.1700
Data Index: 4284776 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0522. Min Range: -4.0522
Max Act: 4.0209. Min Act: -0.1700
Data Index: 5077590 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.9584. Min Act: -0.1700
Data Index: 6985558 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.8959. Min Act: -0.1700
Data Index: 5653704 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.8646. Min Act: -0.1700
Data Index: 6547963 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.8646. Min Act: -0.1700
Data Index: 5117353 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.8646. Min Act: -0.1700
Data Index: 5249185 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.8333. Min Act: -0.1700
Data Index: 3722221 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.8333. Min Act: -0.1700
Data Index: 3434500 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.8333. Min Act: -0.1700
Data Index: 4110690 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.8021. Min Act: -0.1700
Data Index: 6537517 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.8021. Min Act: -0.1700
Data Index: 5642088 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.8021. Min Act: -0.1700
Data Index: 655456 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.8021. Min Act: -0.1700
Data Index: 1397972 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.7864. Min Act: -0.1700
Data Index: 2496179 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.7864. Min Act: -0.1700
Data Index: 5469443 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0522. Min Range: -4.0522
Max Act: 3.7864. Min Act: -0.1700
Data Index: 3289952 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19