Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.8776. Min Act: -0.1700
Data Index: 7495679 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.5651. Min Act: -0.1700
Data Index: 6478008 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.4714. Min Act: -0.1700
Data Index: 939459 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.4714. Min Act: -0.1700
Data Index: 1610451 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.4401. Min Act: -0.1700
Data Index: 8414201 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.4089. Min Act: -0.1700
Data Index: 4423533 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.4089. Min Act: -0.1700
Data Index: 5957269 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.3776. Min Act: -0.1700
Data Index: 1215113 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.2839. Min Act: -0.1700
Data Index: 4955087 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.2839. Min Act: -0.1700
Data Index: 5422603 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.2526. Min Act: -0.1700
Data Index: 4337577 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.1901. Min Act: -0.1700
Data Index: 666905 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.1901. Min Act: -0.1700
Data Index: 2534614 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.1276. Min Act: -0.1700
Data Index: 3762608 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.1276. Min Act: -0.1700
Data Index: 879603 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.0964. Min Act: -0.1700
Data Index: 6409720 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.0651. Min Act: -0.1700
Data Index: 2136223 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.0651. Min Act: -0.1700
Data Index: 6297335 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.0339. Min Act: -0.1700
Data Index: 925628 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8776. Min Range: -7.8776
Max Act: 7.0651. Min Act: -0.1700
Data Index: 4330114 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19