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

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

Neuron 3818 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0362. Min Range: -1.0362

Max Act: 1.0362. Min Act: -0.0001

Data Index: 334694 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.9212. Min Act: -0.0001

Data Index: 245209 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8878. Min Act: -0.0001

Data Index: 1303363 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.9326. Min Act: -0.0001

Data Index: 1280968 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8851. Min Act: -0.0001

Data Index: 176615 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.9046. Min Act: -0.0001

Data Index: 826591 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8856. Min Act: -0.0001

Data Index: 875903 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.9384. Min Act: -0.0001

Data Index: 970846 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8081. Min Act: -0.0001

Data Index: 1310745 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8746. Min Act: -0.0001

Data Index: 1181478 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8360. Min Act: -0.0001

Data Index: 1092952 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8333. Min Act: -0.0001

Data Index: 569844 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.7975. Min Act: -0.0001

Data Index: 864266 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.7524. Min Act: -0.0001

Data Index: 211125 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8228. Min Act: -0.0001

Data Index: 805337 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8493. Min Act: -0.0001

Data Index: 1084958 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8190. Min Act: -0.0001

Data Index: 708452 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8194. Min Act: -0.0001

Data Index: 427579 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.8408. Min Act: -0.0001

Data Index: 395173 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.7222. Min Act: -0.0001

Data Index: 788701 (C4 (Web Text))

Max Activating Token Index: 646