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

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

Neuron 821 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1645570 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1566676 (Python Code)

Max Activating Token Index: 728

Text #2

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1218. Min Act: -0.0000

Data Index: 249361 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1151. Min Act: -0.0000

Data Index: 877416 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1476937 (Python Code)

Max Activating Token Index: 701

Text #5

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1301254 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1596405 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1154065 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1225. Min Act: -0.0001

Data Index: 56425 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1420613 (Python Code)

Max Activating Token Index: 347

Text #10

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1150. Min Act: -0.0000

Data Index: 520516 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1153. Min Act: -0.0000

Data Index: 411639 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1106. Min Act: -0.0000

Data Index: 991087 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1232646 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1380322 (Python Code)

Max Activating Token Index: 1009

Text #15

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1137. Min Act: -0.0000

Data Index: 521767 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1345749 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1047. Min Act: -0.0000

Data Index: 700220 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1008. Min Act: -0.0000

Data Index: 20154 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1576901 (Python Code)

Max Activating Token Index: 518