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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 815 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1679. Min Range: -1.1679

Max Act: 1.1679. Min Act: -0.0000

Data Index: 1122303 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.5601. Min Act: -0.0000

Data Index: 763141 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.5919. Min Act: -0.0000

Data Index: 354271 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.5949. Min Act: -0.0000

Data Index: 744731 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.5950. Min Act: -0.0000

Data Index: 676807 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.6212. Min Act: -0.0000

Data Index: 473090 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1199992 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.5248. Min Act: -0.0000

Data Index: 996002 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.5636. Min Act: -0.0000

Data Index: 114967 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1346976 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.5186. Min Act: -0.0000

Data Index: 464066 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.5094. Min Act: -0.0000

Data Index: 507865 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.4752. Min Act: -0.0000

Data Index: 756402 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.5182. Min Act: -0.0000

Data Index: 308428 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.4847. Min Act: -0.0000

Data Index: 805285 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.4649. Min Act: -0.0000

Data Index: 269399 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.4524. Min Act: -0.0000

Data Index: 145806 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.4613. Min Act: -0.0000

Data Index: 882051 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.4932. Min Act: -0.0000

Data Index: 372395 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.4861. Min Act: -0.0000

Data Index: 413196 (C4 (Web Text))

Max Activating Token Index: 705