Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.9690. Min Act: -0.1700
Data Index: 6200804 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.9215. Min Act: -0.1700
Data Index: 8506460 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.8581. Min Act: -0.1700
Data Index: 8478389 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.8898. Min Act: -0.1700
Data Index: 3804604 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.8898. Min Act: -0.1700
Data Index: 5847950 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.8739. Min Act: -0.1700
Data Index: 3067162 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.8581. Min Act: -0.1700
Data Index: 3594296 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.8263. Min Act: -0.1700
Data Index: 855176 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.8104. Min Act: -0.1700
Data Index: 6432447 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.7944. Min Act: -0.1700
Data Index: 7550887 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.7785. Min Act: -0.1700
Data Index: 1269284 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.7466. Min Act: -0.1700
Data Index: 5962125 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.7626. Min Act: -0.1700
Data Index: 7081759 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.7306. Min Act: -0.1700
Data Index: 6828742 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.7306. Min Act: -0.1700
Data Index: 2945560 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.7306. Min Act: -0.1700
Data Index: 2325814 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.7466. Min Act: -0.1700
Data Index: 4417435 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.7146. Min Act: -0.1700
Data Index: 1441182 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.7306. Min Act: -0.1700
Data Index: 5549270 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9690. Min Range: -2.9690
Max Act: 2.6986. Min Act: -0.1700
Data Index: 5353072 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19