Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.2816. Min Act: -0.1700
Data Index: 6413077 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.2191. Min Act: -0.1700
Data Index: 7369559 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.2191. Min Act: -0.1700
Data Index: 6633060 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.1253. Min Act: -0.1700
Data Index: 4015302 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0628. Min Act: -0.1700
Data Index: 904068 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0316. Min Act: -0.1700
Data Index: 2409290 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0316. Min Act: -0.1700
Data Index: 3732533 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0003. Min Act: -0.1700
Data Index: 763032 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0003. Min Act: -0.1700
Data Index: 1477616 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2816. Min Range: -5.2816
Max Act: 5.0003. Min Act: -0.1700
Data Index: 2136533 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2816. Min Range: -5.2816
Max Act: 4.9691. Min Act: -0.1700
Data Index: 3732534 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2816. Min Range: -5.2816
Max Act: 4.9691. Min Act: -0.1700
Data Index: 929166 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2816. Min Range: -5.2816
Max Act: 4.9066. Min Act: -0.1700
Data Index: 1477590 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2816. Min Range: -5.2816
Max Act: 4.9378. Min Act: -0.1700
Data Index: 1881199 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2816. Min Range: -5.2816
Max Act: 4.9378. Min Act: -0.1700
Data Index: 2698277 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2816. Min Range: -5.2816
Max Act: 4.9378. Min Act: -0.1700
Data Index: 4603219 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2816. Min Range: -5.2816
Max Act: 4.9691. Min Act: -0.1700
Data Index: 8023085 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2816. Min Range: -5.2816
Max Act: 4.9378. Min Act: -0.1700
Data Index: 8154345 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2816. Min Range: -5.2816
Max Act: 4.9691. Min Act: -0.1700
Data Index: 8270682 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2816. Min Range: -5.2816
Max Act: 4.8753. Min Act: -0.1700
Data Index: 6413087 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19