Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3394. Min Range: -8.3394
Max Act: 8.3394. Min Act: -0.1700
Data Index: 3909539 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.8394. Min Act: -0.1700
Data Index: 2782128 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.7144. Min Act: -0.1700
Data Index: 1250898 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.6832. Min Act: -0.1700
Data Index: 6635892 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.6832. Min Act: -0.1700
Data Index: 4601318 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.6519. Min Act: -0.1700
Data Index: 6635893 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.6832. Min Act: -0.1700
Data Index: 6635882 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5894. Min Act: -0.1700
Data Index: 4098307 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5894. Min Act: -0.1700
Data Index: 4140303 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.6207. Min Act: -0.1700
Data Index: 7096294 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5582. Min Act: -0.1700
Data Index: 1585608 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5582. Min Act: -0.1700
Data Index: 7780493 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5582. Min Act: -0.1700
Data Index: 8269643 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5582. Min Act: -0.1700
Data Index: 6196280 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5582. Min Act: -0.1700
Data Index: 7805907 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5582. Min Act: -0.1700
Data Index: 4983668 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5269. Min Act: -0.1700
Data Index: 6011 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5269. Min Act: -0.1700
Data Index: 7779222 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5582. Min Act: -0.1700
Data Index: 6635890 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3394. Min Range: -8.3394
Max Act: 7.5269. Min Act: -0.1700
Data Index: 1560280 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19