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

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

Neuron 345 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1146780 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1435014 (Python Code)

Max Activating Token Index: 561

Text #2

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1230. Min Act: -0.0000

Data Index: 475018 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1131. Min Act: -0.0000

Data Index: 776411 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1079. Min Act: -0.0000

Data Index: 512701 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1109. Min Act: -0.0000

Data Index: 255328 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1208. Min Act: -0.0000

Data Index: 164986 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1592955 (Python Code)

Max Activating Token Index: 597

Text #8

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1079. Min Act: -0.0000

Data Index: 190777 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1015. Min Act: -0.0000

Data Index: 894934 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1413966 (Python Code)

Max Activating Token Index: 482

Text #11

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1045. Min Act: -0.0000

Data Index: 119707 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0960. Min Act: -0.0000

Data Index: 274874 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1027. Min Act: -0.0000

Data Index: 252958 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0988. Min Act: -0.0000

Data Index: 207817 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0980. Min Act: -0.0000

Data Index: 278082 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1361811 (Python Code)

Max Activating Token Index: 1017

Text #17

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0936. Min Act: -0.0000

Data Index: 56775 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0929. Min Act: -0.0000

Data Index: 423634 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0951. Min Act: -0.0000

Data Index: 176278 (C4 (Web Text))

Max Activating Token Index: 567