Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6277 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.4521. Min Act: -0.1700
Data Index: 4456687 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.3271. Min Act: -0.1700
Data Index: 7029505 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2959. Min Act: -0.1700
Data Index: 4913067 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2646. Min Act: -0.1700
Data Index: 6292032 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2021. Min Act: -0.1700
Data Index: 4790765 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 3861453 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2334. Min Act: -0.1700
Data Index: 8327734 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1396. Min Act: -0.1700
Data Index: 7430452 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 5954724 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 8243312 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 4797465 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1396. Min Act: -0.1700
Data Index: 3326239 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1396. Min Act: -0.1700
Data Index: 1403899 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1396. Min Act: -0.1700
Data Index: 2945508 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1396. Min Act: -0.1700
Data Index: 2552686 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1396. Min Act: -0.1700
Data Index: 374414 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1084. Min Act: -0.1700
Data Index: 1208209 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1396. Min Act: -0.1700
Data Index: 7315561 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1084. Min Act: -0.1700
Data Index: 7421693 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1084. Min Act: -0.1700
Data Index: 4256171 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19