Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5519 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1221. Min Range: -7.1221
Max Act: 7.1221. Min Act: -0.1700
Data Index: 602460 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1221. Min Range: -7.1221
Max Act: 7.0909. Min Act: -0.1700
Data Index: 3712800 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1221. Min Range: -7.1221
Max Act: 7.0909. Min Act: -0.1700
Data Index: 8719913 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1221. Min Range: -7.1221
Max Act: 7.0596. Min Act: -0.1700
Data Index: 5053619 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.8409. Min Act: -0.1700
Data Index: 5287168 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.7784. Min Act: -0.1700
Data Index: 7030687 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.7784. Min Act: -0.1700
Data Index: 2034868 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.7159. Min Act: -0.1700
Data Index: 6543308 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.6846. Min Act: -0.1700
Data Index: 2693515 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.6534. Min Act: -0.1700
Data Index: 8825340 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.5284. Min Act: -0.1700
Data Index: 2533558 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.4659. Min Act: -0.1700
Data Index: 7678842 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.4971. Min Act: -0.1700
Data Index: 2260886 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.4346. Min Act: -0.1700
Data Index: 2672565 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.4346. Min Act: -0.1700
Data Index: 6310035 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.4346. Min Act: -0.1700
Data Index: 1208175 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.4346. Min Act: -0.1700
Data Index: 6343048 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.4346. Min Act: -0.1700
Data Index: 5179382 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.4034. Min Act: -0.1700
Data Index: 2898577 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1221. Min Range: -7.1221
Max Act: 6.4346. Min Act: -0.1700
Data Index: 1616977 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19