Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2803 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0194. Min Range: -5.0194
Max Act: 5.0194. Min Act: -0.1700
Data Index: 4283920 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.9569. Min Act: -0.1700
Data Index: 1787378 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.8632. Min Act: -0.1700
Data Index: 4504500 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.8319. Min Act: -0.1700
Data Index: 2176605 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.7069. Min Act: -0.1700
Data Index: 3901665 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.5507. Min Act: -0.1700
Data Index: 3301908 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.5194. Min Act: -0.1700
Data Index: 7344658 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.5194. Min Act: -0.1700
Data Index: 3066234 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.5507. Min Act: -0.1700
Data Index: 3188773 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.5194. Min Act: -0.1700
Data Index: 6392276 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.5194. Min Act: -0.1700
Data Index: 7010525 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.4882. Min Act: -0.1700
Data Index: 7212285 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.4882. Min Act: -0.1700
Data Index: 1562745 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.4882. Min Act: -0.1700
Data Index: 3409881 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.4882. Min Act: -0.1700
Data Index: 5403566 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.4569. Min Act: -0.1700
Data Index: 1333403 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.4569. Min Act: -0.1700
Data Index: 175475 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.4569. Min Act: -0.1700
Data Index: 4967124 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.4569. Min Act: -0.1700
Data Index: 5944137 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.4257. Min Act: -0.1700
Data Index: 4301332 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19