Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.4732. Min Act: -0.1700
Data Index: 2117099 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.2857. Min Act: -0.1700
Data Index: 3682582 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.2545. Min Act: -0.1700
Data Index: 1011401 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.2232. Min Act: -0.1700
Data Index: 6101692 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.1607. Min Act: -0.1700
Data Index: 5636279 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.0982. Min Act: -0.1700
Data Index: 7490712 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.0982. Min Act: -0.1700
Data Index: 8687394 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.1295. Min Act: -0.1700
Data Index: 3245251 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.1295. Min Act: -0.1700
Data Index: 2097767 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.0670. Min Act: -0.1700
Data Index: 3652773 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.0670. Min Act: -0.1700
Data Index: 7081424 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.0357. Min Act: -0.1700
Data Index: 123104 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.0357. Min Act: -0.1700
Data Index: 7578922 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.0357. Min Act: -0.1700
Data Index: 393793 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4732. Min Range: -6.4732
Max Act: 6.0045. Min Act: -0.1700
Data Index: 2849935 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4732. Min Range: -6.4732
Max Act: 5.9420. Min Act: -0.1700
Data Index: 28369 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4732. Min Range: -6.4732
Max Act: 5.9420. Min Act: -0.1700
Data Index: 1366575 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4732. Min Range: -6.4732
Max Act: 5.9732. Min Act: -0.1700
Data Index: 7798605 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4732. Min Range: -6.4732
Max Act: 5.9420. Min Act: -0.1700
Data Index: 8566247 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4732. Min Range: -6.4732
Max Act: 5.9420. Min Act: -0.1700
Data Index: 7368380 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19