Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1826. Min Range: -4.1826
Max Act: 4.1826. Min Act: -0.1700
Data Index: 2423821 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1826. Min Range: -4.1826
Max Act: 4.1201. Min Act: -0.1700
Data Index: 6447887 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1826. Min Range: -4.1826
Max Act: 4.0575. Min Act: -0.1700
Data Index: 8057508 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1826. Min Range: -4.1826
Max Act: 4.0263. Min Act: -0.1700
Data Index: 7975771 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1826. Min Range: -4.1826
Max Act: 4.0263. Min Act: -0.1700
Data Index: 4591393 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9950. Min Act: -0.1700
Data Index: 5356269 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9950. Min Act: -0.1700
Data Index: 7266815 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9950. Min Act: -0.1700
Data Index: 7012438 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9325. Min Act: -0.1700
Data Index: 3544837 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9638. Min Act: -0.1700
Data Index: 2898727 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9325. Min Act: -0.1700
Data Index: 1235698 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9638. Min Act: -0.1700
Data Index: 5271417 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9325. Min Act: -0.1700
Data Index: 3574766 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9012. Min Act: -0.1700
Data Index: 676563 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9012. Min Act: -0.1700
Data Index: 6935228 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9012. Min Act: -0.1700
Data Index: 2892321 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9012. Min Act: -0.1700
Data Index: 447249 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.9325. Min Act: -0.1700
Data Index: 4427589 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.8700. Min Act: -0.1700
Data Index: 2400390 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1826. Min Range: -4.1826
Max Act: 3.8387. Min Act: -0.1700
Data Index: 744982 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19