Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5329 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.9619. Min Act: -0.1700
Data Index: 5174 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.4619. Min Act: -0.1700
Data Index: 2982813 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.2119. Min Act: -0.1700
Data Index: 2524017 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.1806. Min Act: -0.1700
Data Index: 6761324 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.1806. Min Act: -0.1700
Data Index: 7005831 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.1181. Min Act: -0.1700
Data Index: 4030238 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.9619. Min Act: -0.1700
Data Index: 1976910 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.9306. Min Act: -0.1700
Data Index: 1629780 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.8994. Min Act: -0.1700
Data Index: 7178961 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.8994. Min Act: -0.1700
Data Index: 2916206 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.8056. Min Act: -0.1700
Data Index: 863311 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.8369. Min Act: -0.1700
Data Index: 3122080 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.8369. Min Act: -0.1700
Data Index: 271279 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.7744. Min Act: -0.1700
Data Index: 5379720 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.7744. Min Act: -0.1700
Data Index: 8513018 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.7744. Min Act: -0.1700
Data Index: 3469222 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.7744. Min Act: -0.1700
Data Index: 1856564 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.8056. Min Act: -0.1700
Data Index: 1129595 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.7431. Min Act: -0.1700
Data Index: 1676558 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9619. Min Range: -6.9619
Max Act: 5.7431. Min Act: -0.1700
Data Index: 3815526 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19