Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.5861. Min Act: -0.1700
Data Index: 2302755 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.5549. Min Act: -0.1700
Data Index: 5168266 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.4611. Min Act: -0.1700
Data Index: 862702 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.4299. Min Act: -0.1700
Data Index: 1872006 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.1799. Min Act: -0.1700
Data Index: 194154 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.1799. Min Act: -0.1700
Data Index: 7007342 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.1174. Min Act: -0.1700
Data Index: 7570582 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.0861. Min Act: -0.1700
Data Index: 6881111 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.0549. Min Act: -0.1700
Data Index: 3681225 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.0861. Min Act: -0.1700
Data Index: 7285011 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.0549. Min Act: -0.1700
Data Index: 1610725 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.0549. Min Act: -0.1700
Data Index: 544890 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.0236. Min Act: -0.1700
Data Index: 6890022 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.0236. Min Act: -0.1700
Data Index: 8519294 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.0236. Min Act: -0.1700
Data Index: 2346919 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5861. Min Range: -7.5861
Max Act: 7.0236. Min Act: -0.1700
Data Index: 2097217 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5861. Min Range: -7.5861
Max Act: 6.9611. Min Act: -0.1700
Data Index: 2872060 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5861. Min Range: -7.5861
Max Act: 6.9611. Min Act: -0.1700
Data Index: 4391062 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5861. Min Range: -7.5861
Max Act: 6.9611. Min Act: -0.1700
Data Index: 2901892 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5861. Min Range: -7.5861
Max Act: 6.8986. Min Act: -0.1700
Data Index: 1009037 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19