Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 716 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.9096. Min Act: -0.1700
Data Index: 4079556 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.7221. Min Act: -0.1700
Data Index: 6203323 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.6596. Min Act: -0.1700
Data Index: 4390469 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.6596. Min Act: -0.1700
Data Index: 6688044 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.5971. Min Act: -0.1700
Data Index: 394477 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.5346. Min Act: -0.1700
Data Index: 7773955 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.5658. Min Act: -0.1700
Data Index: 2714817 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.5346. Min Act: -0.1700
Data Index: 1933762 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.5033. Min Act: -0.1700
Data Index: 1464936 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.4721. Min Act: -0.1700
Data Index: 2846150 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.4096. Min Act: -0.1700
Data Index: 975632 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.4408. Min Act: -0.1700
Data Index: 921237 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.4408. Min Act: -0.1700
Data Index: 3840059 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.4096. Min Act: -0.1700
Data Index: 7886056 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.3783. Min Act: -0.1700
Data Index: 7017412 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.3783. Min Act: -0.1700
Data Index: 8099494 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.3783. Min Act: -0.1700
Data Index: 5965220 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.3471. Min Act: -0.1700
Data Index: 4898599 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.3783. Min Act: -0.1700
Data Index: 7850396 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9096. Min Range: -7.9096
Max Act: 7.3158. Min Act: -0.1700
Data Index: 4104986 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19