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

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

Neuron 1664 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1317. Min Range: -2.1317

Max Act: 2.1240. Min Act: -0.0000

Data Index: 526590 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 2.1317. Min Range: -2.1317

Max Act: 2.1317. Min Act: -0.0000

Data Index: 1176239 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 2.1317. Min Range: -2.1317

Max Act: 2.0141. Min Act: -0.0000

Data Index: 841757 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.8720. Min Act: -0.0000

Data Index: 991186 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.9815. Min Act: -0.0000

Data Index: 944867 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.9355. Min Act: -0.0000

Data Index: 1119643 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.8250. Min Act: -0.0000

Data Index: 988882 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.7846. Min Act: -0.0000

Data Index: 679571 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.7753. Min Act: -0.0000

Data Index: 174715 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.8559. Min Act: -0.0000

Data Index: 1344249 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.8458. Min Act: -0.0000

Data Index: 757722 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.7993. Min Act: -0.0000

Data Index: 819567 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.6967. Min Act: 0.0000

Data Index: 884310 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.7856. Min Act: -0.0000

Data Index: 1300314 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.7718. Min Act: -0.0000

Data Index: 18863 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.6635. Min Act: -0.0000

Data Index: 359345 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.7401. Min Act: -0.0000

Data Index: 194373 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.6041. Min Act: -0.0000

Data Index: 1296465 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.5785. Min Act: -0.0000

Data Index: 151167 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 2.1317. Min Range: -2.1317

Max Act: 1.5600. Min Act: -0.0000

Data Index: 512023 (C4 (Web Text))

Max Activating Token Index: 218