Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3712 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.8314. Min Act: -0.1700
Data Index: 6191824 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.7064. Min Act: -0.1700
Data Index: 7553658 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.6751. Min Act: -0.1700
Data Index: 2862931 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.6126. Min Act: -0.1700
Data Index: 8453097 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.5814. Min Act: -0.1700
Data Index: 6372679 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.6126. Min Act: -0.1700
Data Index: 2844558 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.5814. Min Act: -0.1700
Data Index: 3488473 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.5814. Min Act: -0.1700
Data Index: 6117758 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.5501. Min Act: -0.1700
Data Index: 7248227 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.5501. Min Act: -0.1700
Data Index: 5853816 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.5189. Min Act: -0.1700
Data Index: 1443924 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.4876. Min Act: -0.1700
Data Index: 7772386 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.4876. Min Act: -0.1700
Data Index: 1633400 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.4876. Min Act: -0.1700
Data Index: 3914292 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.4564. Min Act: -0.1700
Data Index: 1675547 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.4564. Min Act: -0.1700
Data Index: 2609036 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.4564. Min Act: -0.1700
Data Index: 373086 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.4564. Min Act: -0.1700
Data Index: 4244683 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.3939. Min Act: -0.1700
Data Index: 4205466 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8314. Min Range: -6.8314
Max Act: 6.4251. Min Act: -0.1700
Data Index: 5563435 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19