Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 697 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.9397. Min Act: -0.1700
Data Index: 2416171 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.9080. Min Act: -0.1700
Data Index: 59 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.9080. Min Act: -0.1700
Data Index: 4589148 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.8604. Min Act: -0.1700
Data Index: 333224 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.8445. Min Act: -0.1700
Data Index: 1077133 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.8763. Min Act: -0.1700
Data Index: 5190528 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.8445. Min Act: -0.1700
Data Index: 7485410 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.8286. Min Act: -0.1700
Data Index: 2416170 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.8127. Min Act: -0.1700
Data Index: 7743312 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.8127. Min Act: -0.1700
Data Index: 4792479 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.7809. Min Act: -0.1700
Data Index: 5748297 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.7809. Min Act: -0.1700
Data Index: 812556 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.7809. Min Act: -0.1700
Data Index: 283724 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.7809. Min Act: -0.1700
Data Index: 3757637 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.7649. Min Act: -0.1700
Data Index: 82361 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.7330. Min Act: -0.1700
Data Index: 6495799 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.7330. Min Act: -0.1700
Data Index: 60 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.7170. Min Act: -0.1700
Data Index: 5473096 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.7010. Min Act: -0.1700
Data Index: 5947789 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9397. Min Range: -2.9397
Max Act: 2.7010. Min Act: -0.1700
Data Index: 6251142 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19