Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2403 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.5361. Min Act: -0.1700
Data Index: 3277 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.5361. Min Act: -0.1700
Data Index: 4791050 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.5048. Min Act: -0.1700
Data Index: 2970371 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.5048. Min Act: -0.1700
Data Index: 2092337 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.5048. Min Act: -0.1700
Data Index: 5017768 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.4423. Min Act: -0.1700
Data Index: 2096726 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.3798. Min Act: -0.1700
Data Index: 1413542 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.4111. Min Act: -0.1700
Data Index: 3137414 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.3798. Min Act: -0.1700
Data Index: 4386781 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.3798. Min Act: -0.1700
Data Index: 264492 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.3486. Min Act: -0.1700
Data Index: 8645037 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.3486. Min Act: -0.1700
Data Index: 1234940 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.3173. Min Act: -0.1700
Data Index: 2718304 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.3173. Min Act: -0.1700
Data Index: 3965569 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2861. Min Act: -0.1700
Data Index: 616275 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2861. Min Act: -0.1700
Data Index: 5858503 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2861. Min Act: -0.1700
Data Index: 4615477 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2548. Min Act: -0.1700
Data Index: 3336185 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2861. Min Act: -0.1700
Data Index: 2395549 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5361. Min Range: -6.5361
Max Act: 6.2236. Min Act: -0.1700
Data Index: 2464733 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19