Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.8986. Min Act: -0.1700
Data Index: 6718063 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.8048. Min Act: -0.1700
Data Index: 2535645 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.8048. Min Act: -0.1700
Data Index: 2024157 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.6798. Min Act: -0.1700
Data Index: 2931413 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.6486. Min Act: -0.1700
Data Index: 7232723 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.6486. Min Act: -0.1700
Data Index: 918964 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.5861. Min Act: -0.1700
Data Index: 4842896 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.6173. Min Act: -0.1700
Data Index: 347426 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.6173. Min Act: -0.1700
Data Index: 8806197 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.5548. Min Act: -0.1700
Data Index: 6383818 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.5861. Min Act: -0.1700
Data Index: 6822918 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.5548. Min Act: -0.1700
Data Index: 5628325 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.5548. Min Act: -0.1700
Data Index: 233799 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.5236. Min Act: -0.1700
Data Index: 5683042 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.5236. Min Act: -0.1700
Data Index: 3516698 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.4923. Min Act: -0.1700
Data Index: 5713876 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.5236. Min Act: -0.1700
Data Index: 7026068 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.5236. Min Act: -0.1700
Data Index: 2435685 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.4611. Min Act: -0.1700
Data Index: 1122673 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8986. Min Range: -5.8986
Max Act: 5.4923. Min Act: -0.1700
Data Index: 1580935 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19