Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 820 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1320836 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8860. Min Act: -0.0000

Data Index: 75932 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9677. Min Act: -0.0000

Data Index: 789568 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1422779 (The Pile)

Max Activating Token Index: 913

Text #4

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9230. Min Act: -0.0000

Data Index: 737384 (The Pile)

Max Activating Token Index: 19

Text #5

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9567. Min Act: -0.0000

Data Index: 215912 (The Pile)

Max Activating Token Index: 167

Text #6

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8402. Min Act: -0.0000

Data Index: 993869 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7392. Min Act: -0.0000

Data Index: 590248 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8581. Min Act: -0.0000

Data Index: 193269 (The Pile)

Max Activating Token Index: 528

Text #9

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1284246 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1513233 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1240485 (The Pile)

Max Activating Token Index: 531

Text #12

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1216837 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7953. Min Act: -0.0000

Data Index: 595875 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1977454 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9379. Min Act: -0.0000

Data Index: 1424929 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1091698 (The Pile)

Max Activating Token Index: 913

Text #17

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1471098 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1434767 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8200. Min Act: -0.0000

Data Index: 66014 (The Pile)

Max Activating Token Index: 760