Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1192 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0006

Data Index: 800744 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0343. Min Act: -0.0006

Data Index: 702130 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0324. Min Act: -0.0006

Data Index: 784497 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0310. Min Act: -0.0006

Data Index: 1234603 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0328. Min Act: -0.0006

Data Index: 1018077 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0338. Min Act: -0.0006

Data Index: 962010 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0334. Min Act: -0.0006

Data Index: 103642 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0320. Min Act: -0.0006

Data Index: 1128416 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0314. Min Act: -0.0006

Data Index: 1267033 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0319. Min Act: -0.0006

Data Index: 196844 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0324. Min Act: -0.0006

Data Index: 77939 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0312. Min Act: -0.0006

Data Index: 1268217 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0332. Min Act: -0.0006

Data Index: 975924 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0310. Min Act: -0.0006

Data Index: 936080 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0315. Min Act: -0.0006

Data Index: 174143 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0298. Min Act: -0.0006

Data Index: 1030334 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0302. Min Act: -0.0006

Data Index: 439946 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0307. Min Act: -0.0006

Data Index: 300586 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0301. Min Act: -0.0006

Data Index: 302831 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0310. Min Act: -0.0006

Data Index: 619634 (C4 (Web Text))

Max Activating Token Index: 40