Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5402 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.4833. Min Act: -0.1700
Data Index: 8342909 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.4521. Min Act: -0.1700
Data Index: 1494345 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.4208. Min Act: -0.1700
Data Index: 8043925 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.3896. Min Act: -0.1700
Data Index: 6596425 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.3896. Min Act: -0.1700
Data Index: 5314050 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.3583. Min Act: -0.1700
Data Index: 4191185 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.3583. Min Act: -0.1700
Data Index: 586102 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.3583. Min Act: -0.1700
Data Index: 1743091 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.3271. Min Act: -0.1700
Data Index: 2438933 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.3271. Min Act: -0.1700
Data Index: 3009254 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.2333. Min Act: -0.1700
Data Index: 6610477 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.2333. Min Act: -0.1700
Data Index: 1878709 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.2021. Min Act: -0.1700
Data Index: 8320484 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.1708. Min Act: -0.1700
Data Index: 2822802 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.1708. Min Act: -0.1700
Data Index: 1329463 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.1395. Min Act: -0.1700
Data Index: 8576630 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.1395. Min Act: -0.1700
Data Index: 3394131 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.1395. Min Act: -0.1700
Data Index: 590526 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.1395. Min Act: -0.1700
Data Index: 3679370 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4833. Min Range: -4.4833
Max Act: 4.1395. Min Act: -0.1700
Data Index: 7222006 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19