Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.8240. Min Act: -0.1700
Data Index: 6999144 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.7615. Min Act: -0.1700
Data Index: 1227391 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.7928. Min Act: -0.1700
Data Index: 6985321 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.7771. Min Act: -0.1700
Data Index: 933518 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6989. Min Act: -0.1700
Data Index: 300803 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6833. Min Act: -0.1700
Data Index: 1859640 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6676. Min Act: -0.1700
Data Index: 4467665 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6833. Min Act: -0.1700
Data Index: 3061828 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6833. Min Act: -0.1700
Data Index: 5361573 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6520. Min Act: -0.1700
Data Index: 647613 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6833. Min Act: -0.1700
Data Index: 8785963 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6520. Min Act: -0.1700
Data Index: 1441328 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6520. Min Act: -0.1700
Data Index: 6048377 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6207. Min Act: -0.1700
Data Index: 358005 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6050. Min Act: -0.1700
Data Index: 2358126 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6050. Min Act: -0.1700
Data Index: 2829455 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.6050. Min Act: -0.1700
Data Index: 5112546 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.5737. Min Act: -0.1700
Data Index: 8148157 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.5737. Min Act: -0.1700
Data Index: 647612 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8240. Min Range: -3.8240
Max Act: 3.5268. Min Act: -0.1700
Data Index: 933519 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19