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

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

Neuron 2972 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1383. Min Range: -1.1383

Max Act: 1.1383. Min Act: -0.0001

Data Index: 375592 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.9313. Min Act: -0.0002

Data Index: 1245198 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8417. Min Act: -0.0002

Data Index: 1296471 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8393. Min Act: -0.0002

Data Index: 874956 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8311. Min Act: -0.0002

Data Index: 194541 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.6709. Min Act: -0.0002

Data Index: 534934 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7246. Min Act: -0.0002

Data Index: 725164 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8488. Min Act: -0.0002

Data Index: 741825 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7408. Min Act: -0.0002

Data Index: 473589 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7547. Min Act: -0.0002

Data Index: 498317 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7896. Min Act: -0.0001

Data Index: 495534 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8244. Min Act: -0.0001

Data Index: 1030336 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7859. Min Act: -0.0001

Data Index: 1170344 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7906. Min Act: -0.0001

Data Index: 368221 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.6819. Min Act: -0.0002

Data Index: 1232849 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7328. Min Act: -0.0002

Data Index: 345515 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7135. Min Act: -0.0002

Data Index: 870661 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7455. Min Act: -0.0002

Data Index: 971112 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7479. Min Act: -0.0001

Data Index: 1321185 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7212. Min Act: -0.0001

Data Index: 1031268 (C4 (Web Text))

Max Activating Token Index: 526