Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4952 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.8254. Min Act: -0.1700
Data Index: 4598420 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.6691. Min Act: -0.1700
Data Index: 2576020 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.6379. Min Act: -0.1700
Data Index: 1967060 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.6066. Min Act: -0.1700
Data Index: 190983 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.4504. Min Act: -0.1700
Data Index: 4495925 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.4504. Min Act: -0.1700
Data Index: 8322810 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.4191. Min Act: -0.1700
Data Index: 5059954 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.3566. Min Act: -0.1700
Data Index: 6336795 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.2941. Min Act: -0.1700
Data Index: 8346454 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.3254. Min Act: -0.1700
Data Index: 909816 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.3254. Min Act: -0.1700
Data Index: 1826635 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.3566. Min Act: -0.1700
Data Index: 4097347 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.2941. Min Act: -0.1700
Data Index: 1160588 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.2629. Min Act: -0.1700
Data Index: 6980839 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.2629. Min Act: -0.1700
Data Index: 1440614 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.2316. Min Act: -0.1700
Data Index: 4649322 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.2316. Min Act: -0.1700
Data Index: 746876 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.2316. Min Act: -0.1700
Data Index: 6652522 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.2316. Min Act: -0.1700
Data Index: 4573831 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.2629. Min Act: -0.1700
Data Index: 8279735 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19