Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6328 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.7885. Min Act: -0.1700
Data Index: 2529694 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.7573. Min Act: -0.1700
Data Index: 6383549 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.7260. Min Act: -0.1700
Data Index: 5611038 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.6635. Min Act: -0.1700
Data Index: 8032226 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.6635. Min Act: -0.1700
Data Index: 2751775 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.6635. Min Act: -0.1700
Data Index: 5004490 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.6010. Min Act: -0.1700
Data Index: 7992850 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.5698. Min Act: -0.1700
Data Index: 4391971 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.6010. Min Act: -0.1700
Data Index: 1457 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.5698. Min Act: -0.1700
Data Index: 6846444 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.5385. Min Act: -0.1700
Data Index: 1940526 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.5073. Min Act: -0.1700
Data Index: 6999391 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.4760. Min Act: -0.1700
Data Index: 7283893 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.4760. Min Act: -0.1700
Data Index: 3335416 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.4760. Min Act: -0.1700
Data Index: 3516134 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.4760. Min Act: -0.1700
Data Index: 6011301 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.4448. Min Act: -0.1700
Data Index: 3666107 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.4135. Min Act: -0.1700
Data Index: 699056 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.3823. Min Act: -0.1700
Data Index: 8141381 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7885. Min Range: -6.7885
Max Act: 6.3510. Min Act: -0.1700
Data Index: 6502082 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19