Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.7640. Min Act: -0.1700
Data Index: 572502 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.7953. Min Act: -0.1700
Data Index: 6471916 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.7640. Min Act: -0.1700
Data Index: 7633782 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.7328. Min Act: -0.1700
Data Index: 7126485 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.6703. Min Act: -0.1700
Data Index: 5260615 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.5765. Min Act: -0.1700
Data Index: 759309 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.6078. Min Act: -0.1700
Data Index: 2682430 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.5765. Min Act: -0.1700
Data Index: 7458641 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.5765. Min Act: -0.1700
Data Index: 677827 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.5453. Min Act: -0.1700
Data Index: 3878423 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.5453. Min Act: -0.1700
Data Index: 2850329 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.5453. Min Act: -0.1700
Data Index: 1653872 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.5140. Min Act: -0.1700
Data Index: 4231667 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.4828. Min Act: -0.1700
Data Index: 8486149 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.4515. Min Act: -0.1700
Data Index: 4469646 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.4203. Min Act: -0.1700
Data Index: 6165319 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.4203. Min Act: -0.1700
Data Index: 7663662 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.4203. Min Act: -0.1700
Data Index: 2869275 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.4203. Min Act: -0.1700
Data Index: 5488875 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7953. Min Range: -6.7953
Max Act: 6.4203. Min Act: -0.1700
Data Index: 4310054 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19