Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.6124. Min Act: -0.1700
Data Index: 419170 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.4562. Min Act: -0.1700
Data Index: 6513919 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.2999. Min Act: -0.1700
Data Index: 3669215 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.2374. Min Act: -0.1700
Data Index: 2006739 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.2374. Min Act: -0.1700
Data Index: 3561506 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.1437. Min Act: -0.1700
Data Index: 7160478 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.1437. Min Act: -0.1700
Data Index: 6848561 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.1124. Min Act: -0.1700
Data Index: 2313096 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.0812. Min Act: -0.1700
Data Index: 1860698 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.0499. Min Act: -0.1700
Data Index: 567293 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.0812. Min Act: -0.1700
Data Index: 6663324 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.0187. Min Act: -0.1700
Data Index: 2345045 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6124. Min Range: -6.6124
Max Act: 6.0499. Min Act: -0.1700
Data Index: 6946937 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6124. Min Range: -6.6124
Max Act: 5.9874. Min Act: -0.1700
Data Index: 7673898 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6124. Min Range: -6.6124
Max Act: 5.9562. Min Act: -0.1700
Data Index: 1635856 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6124. Min Range: -6.6124
Max Act: 5.9249. Min Act: -0.1700
Data Index: 6503322 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6124. Min Range: -6.6124
Max Act: 5.9249. Min Act: -0.1700
Data Index: 6584833 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6124. Min Range: -6.6124
Max Act: 5.8937. Min Act: -0.1700
Data Index: 4553263 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6124. Min Range: -6.6124
Max Act: 5.8937. Min Act: -0.1700
Data Index: 4390157 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6124. Min Range: -6.6124
Max Act: 5.8312. Min Act: -0.1700
Data Index: 6434196 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19