Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.5100. Min Act: -0.1700
Data Index: 859044 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.4787. Min Act: -0.1700
Data Index: 4824913 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.3537. Min Act: -0.1700
Data Index: 7514042 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.3850. Min Act: -0.1700
Data Index: 7514043 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.3537. Min Act: -0.1700
Data Index: 859037 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.2912. Min Act: -0.1700
Data Index: 4478296 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.2912. Min Act: -0.1700
Data Index: 8084262 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.2600. Min Act: -0.1700
Data Index: 1722150 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.2912. Min Act: -0.1700
Data Index: 7514044 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.2287. Min Act: -0.1700
Data Index: 2762366 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.2287. Min Act: -0.1700
Data Index: 823229 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.1975. Min Act: -0.1700
Data Index: 4208383 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.1662. Min Act: -0.1700
Data Index: 7120994 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.1662. Min Act: -0.1700
Data Index: 7853699 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.1662. Min Act: -0.1700
Data Index: 1483396 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.1350. Min Act: -0.1700
Data Index: 7514037 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.1350. Min Act: -0.1700
Data Index: 2929535 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.1350. Min Act: -0.1700
Data Index: 2929534 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.1350. Min Act: -0.1700
Data Index: 7514041 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5100. Min Range: -5.5100
Max Act: 5.1037. Min Act: -0.1700
Data Index: 3573963 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19