Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5072 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.9904. Min Act: -0.1700
Data Index: 5572073 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.7716. Min Act: -0.1700
Data Index: 3296191 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.7716. Min Act: -0.1700
Data Index: 6133099 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.7559. Min Act: -0.1700
Data Index: 5497800 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.7403. Min Act: -0.1700
Data Index: 466260 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6777. Min Act: -0.1700
Data Index: 8413863 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.7090. Min Act: -0.1700
Data Index: 3005348 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6934. Min Act: -0.1700
Data Index: 1530258 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6934. Min Act: -0.1700
Data Index: 6133093 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6777. Min Act: -0.1700
Data Index: 5705872 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6777. Min Act: -0.1700
Data Index: 6133092 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6777. Min Act: -0.1700
Data Index: 3515993 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6621. Min Act: -0.1700
Data Index: 7524321 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6308. Min Act: -0.1700
Data Index: 2563886 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6621. Min Act: -0.1700
Data Index: 5185305 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6308. Min Act: -0.1700
Data Index: 1322454 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6464. Min Act: -0.1700
Data Index: 4753547 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.5995. Min Act: -0.1700
Data Index: 3114188 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6151. Min Act: -0.1700
Data Index: 4310923 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9904. Min Range: -3.9904
Max Act: 3.6151. Min Act: -0.1700
Data Index: 5424227 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19