Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4579 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3525. Min Range: -7.3525
Max Act: 7.3525. Min Act: -0.1700
Data Index: 5936944 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3525. Min Range: -7.3525
Max Act: 7.1337. Min Act: -0.1700
Data Index: 1295493 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.9150. Min Act: -0.1700
Data Index: 533889 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.8837. Min Act: -0.1700
Data Index: 1199543 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.8212. Min Act: -0.1700
Data Index: 4121724 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.7900. Min Act: -0.1700
Data Index: 7548239 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.7900. Min Act: -0.1700
Data Index: 6245040 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.7587. Min Act: -0.1700
Data Index: 2951018 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.7587. Min Act: -0.1700
Data Index: 5761799 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.7587. Min Act: -0.1700
Data Index: 6623514 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.7275. Min Act: -0.1700
Data Index: 4802134 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.6962. Min Act: -0.1700
Data Index: 247705 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.6962. Min Act: -0.1700
Data Index: 3973168 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.6962. Min Act: -0.1700
Data Index: 4680619 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.6962. Min Act: -0.1700
Data Index: 5761797 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.7275. Min Act: -0.1700
Data Index: 4651351 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.6962. Min Act: -0.1700
Data Index: 5599380 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.6650. Min Act: -0.1700
Data Index: 6313985 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.6962. Min Act: -0.1700
Data Index: 3217911 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3525. Min Range: -7.3525
Max Act: 6.6650. Min Act: -0.1700
Data Index: 1795215 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19