Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5900 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1449. Min Range: -5.1449
Max Act: 5.1449. Min Act: -0.1700
Data Index: 5767939 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1449. Min Range: -5.1449
Max Act: 5.1137. Min Act: -0.1700
Data Index: 4443252 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1449. Min Range: -5.1449
Max Act: 5.0824. Min Act: -0.1700
Data Index: 324885 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1449. Min Range: -5.1449
Max Act: 5.0199. Min Act: -0.1700
Data Index: 5871334 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1449. Min Range: -5.1449
Max Act: 5.0199. Min Act: -0.1700
Data Index: 5059793 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1449. Min Range: -5.1449
Max Act: 5.0199. Min Act: -0.1700
Data Index: 5581510 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.9262. Min Act: -0.1700
Data Index: 72457 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.9262. Min Act: -0.1700
Data Index: 6941377 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.9262. Min Act: -0.1700
Data Index: 5550188 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.9262. Min Act: -0.1700
Data Index: 3424936 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.8949. Min Act: -0.1700
Data Index: 5550191 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.8949. Min Act: -0.1700
Data Index: 1498605 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.8637. Min Act: -0.1700
Data Index: 1110285 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.8637. Min Act: -0.1700
Data Index: 5447599 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.8012. Min Act: -0.1700
Data Index: 5174840 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.8324. Min Act: -0.1700
Data Index: 3382686 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.8324. Min Act: -0.1700
Data Index: 3901493 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.8324. Min Act: -0.1700
Data Index: 6063834 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.8012. Min Act: -0.1700
Data Index: 6063829 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1449. Min Range: -5.1449
Max Act: 4.8012. Min Act: -0.1700
Data Index: 5960973 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19