Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.5416. Min Act: -0.1700
Data Index: 1807369 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.4791. Min Act: -0.1700
Data Index: 8421299 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.4791. Min Act: -0.1700
Data Index: 7289182 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.4791. Min Act: -0.1700
Data Index: 2749305 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.4479. Min Act: -0.1700
Data Index: 1447229 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.3854. Min Act: -0.1700
Data Index: 2399582 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.3541. Min Act: -0.1700
Data Index: 3380096 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.3229. Min Act: -0.1700
Data Index: 6611993 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.2604. Min Act: -0.1700
Data Index: 889376 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.2291. Min Act: -0.1700
Data Index: 8748334 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.2291. Min Act: -0.1700
Data Index: 2485722 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.1979. Min Act: -0.1700
Data Index: 1532622 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.1666. Min Act: -0.1700
Data Index: 4938719 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.1666. Min Act: -0.1700
Data Index: 7332882 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.1666. Min Act: -0.1700
Data Index: 8224382 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.1354. Min Act: -0.1700
Data Index: 7030061 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.1354. Min Act: -0.1700
Data Index: 3686064 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.1041. Min Act: -0.1700
Data Index: 4436762 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.1354. Min Act: -0.1700
Data Index: 1902439 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5416. Min Range: -5.5416
Max Act: 5.1354. Min Act: -0.1700
Data Index: 7379332 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19