Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5272 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.2233. Min Act: -0.1700
Data Index: 4179939 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.1295. Min Act: -0.1700
Data Index: 5105306 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.1608. Min Act: -0.1700
Data Index: 6636260 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.1608. Min Act: -0.1700
Data Index: 7679 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.1295. Min Act: -0.1700
Data Index: 6562949 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0983. Min Act: -0.1700
Data Index: 150288 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0983. Min Act: -0.1700
Data Index: 5059704 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0358. Min Act: -0.1700
Data Index: 1616052 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0358. Min Act: -0.1700
Data Index: 6777592 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0358. Min Act: -0.1700
Data Index: 3996905 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0358. Min Act: -0.1700
Data Index: 2018510 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0045. Min Act: -0.1700
Data Index: 5430789 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2233. Min Range: -5.2233
Max Act: 4.9733. Min Act: -0.1700
Data Index: 2400106 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0358. Min Act: -0.1700
Data Index: 4886378 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0358. Min Act: -0.1700
Data Index: 3766047 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0045. Min Act: -0.1700
Data Index: 7477577 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0045. Min Act: -0.1700
Data Index: 5685801 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0045. Min Act: -0.1700
Data Index: 3636632 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2233. Min Range: -5.2233
Max Act: 5.0045. Min Act: -0.1700
Data Index: 88361 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2233. Min Range: -5.2233
Max Act: 4.9420. Min Act: -0.1700
Data Index: 891685 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19