Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.2171. Min Act: -0.1700
Data Index: 2811209 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.1859. Min Act: -0.1700
Data Index: 7136447 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.1859. Min Act: -0.1700
Data Index: 2074895 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.1546. Min Act: -0.1700
Data Index: 6788587 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.1233. Min Act: -0.1700
Data Index: 4788806 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.0921. Min Act: -0.1700
Data Index: 1262218 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.0608. Min Act: -0.1700
Data Index: 4431065 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.0921. Min Act: -0.1700
Data Index: 4441153 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.0296. Min Act: -0.1700
Data Index: 2607360 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.0296. Min Act: -0.1700
Data Index: 820851 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.0296. Min Act: -0.1700
Data Index: 623967 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.0296. Min Act: -0.1700
Data Index: 5895125 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9983. Min Act: -0.1700
Data Index: 7859577 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.0296. Min Act: -0.1700
Data Index: 1644659 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9983. Min Act: -0.1699
Data Index: 2709885 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9983. Min Act: -0.1700
Data Index: 7942117 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9358. Min Act: -0.1700
Data Index: 5731721 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9670. Min Act: -0.1700
Data Index: 56117 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9670. Min Act: -0.1700
Data Index: 4109121 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9670. Min Act: -0.1699
Data Index: 4936038 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19