Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1946 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.8053. Min Act: -0.0000

Data Index: 495340 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1607204 (The Pile)

Max Activating Token Index: 812

Text #2

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7866. Min Act: -0.0000

Data Index: 154736 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7644. Min Act: -0.0000

Data Index: 272358 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1665275 (The Pile)

Max Activating Token Index: 38

Text #5

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7308. Min Act: -0.0000

Data Index: 61526 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1152899 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1504985 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7711. Min Act: -0.0000

Data Index: 230236 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1719298 (The Pile)

Max Activating Token Index: 233

Text #10

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7154. Min Act: -0.0000

Data Index: 144933 (The Pile)

Max Activating Token Index: 1018

Text #11

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1584755 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1880273 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1678555 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7189. Min Act: -0.0000

Data Index: 100216 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1726822 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1093335 (The Pile)

Max Activating Token Index: 699

Text #17

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.6997. Min Act: -0.0000

Data Index: 224197 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1756052 (The Pile)

Max Activating Token Index: 365

Text #19

Max Range: 0.8318. Min Range: -0.8318

Max Act: 0.6613. Min Act: -0.0000

Data Index: 231369 (The Pile)

Max Activating Token Index: 71