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

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

Neuron 4276 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.7240. Min Act: -0.0001

Data Index: 32012 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.3607. Min Act: -0.0001

Data Index: 563524 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.5526. Min Act: -0.0001

Data Index: 532187 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.4217. Min Act: -0.0001

Data Index: 375607 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.4767. Min Act: -0.0001

Data Index: 474947 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.3043. Min Act: -0.0001

Data Index: 1115750 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.3246. Min Act: -0.0001

Data Index: 1086801 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.3765. Min Act: -0.0001

Data Index: 241697 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.3595. Min Act: -0.0001

Data Index: 722940 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.3497. Min Act: -0.0001

Data Index: 892672 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.3172. Min Act: -0.0001

Data Index: 207670 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.3304. Min Act: -0.0001

Data Index: 932096 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1687. Min Act: -0.0001

Data Index: 1069213 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.3038. Min Act: -0.0001

Data Index: 737275 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2675. Min Act: -0.0001

Data Index: 932812 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2904. Min Act: -0.0001

Data Index: 1200545 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2890. Min Act: -0.0001

Data Index: 1265885 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2967. Min Act: -0.0001

Data Index: 673191 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2143. Min Act: -0.0001

Data Index: 536008 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1396. Min Act: -0.0001

Data Index: 650508 (C4 (Web Text))

Max Activating Token Index: 336