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

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

Neuron 2120 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2451. Min Act: -0.0001

Data Index: 600996 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2411. Min Act: -0.0001

Data Index: 1300305 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2230. Min Act: -0.0001

Data Index: 678109 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2112. Min Act: -0.0001

Data Index: 177229 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2067. Min Act: -0.0001

Data Index: 674007 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2045. Min Act: -0.0001

Data Index: 594427 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.1557. Min Act: -0.0001

Data Index: 989921 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.1295. Min Act: -0.0001

Data Index: 669552 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.1264. Min Act: -0.0001

Data Index: 1586681 (Python Code)

Max Activating Token Index: 149

Text #9

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.1271. Min Act: -0.0001

Data Index: 377773 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.1173. Min Act: -0.0001

Data Index: 330951 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1059722 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.1177. Min Act: -0.0001

Data Index: 350270 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.1138. Min Act: -0.0001

Data Index: 30353 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1305055 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.1043. Min Act: -0.0001

Data Index: 307027 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.0970. Min Act: -0.0001

Data Index: 295488 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1465613 (Python Code)

Max Activating Token Index: 1021

Text #18

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.0988. Min Act: -0.0001

Data Index: 870441 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1425455 (Python Code)

Max Activating Token Index: 773