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

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

Neuron 3280 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: 0.1986. Min Range: -0.1986

Max Act: 0.1828. Min Act: -0.0001

Data Index: 78431 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1272049 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1264628 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1660. Min Act: -0.0001

Data Index: 49706 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1128614 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1672. Min Act: -0.0001

Data Index: 795506 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1603. Min Act: -0.0001

Data Index: 588870 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1576. Min Act: -0.0001

Data Index: 651593 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1159771 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1406. Min Act: -0.0001

Data Index: 123315 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1311. Min Act: -0.0001

Data Index: 258966 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1140609 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1119439 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1404. Min Act: -0.0001

Data Index: 817430 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1286354 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1136. Min Act: -0.0001

Data Index: 63112 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1252. Min Act: -0.0001

Data Index: 421486 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1190. Min Act: -0.0001

Data Index: 461614 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1266. Min Act: -0.0001

Data Index: 17416 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1161. Min Act: -0.0001

Data Index: 765831 (C4 (Web Text))

Max Activating Token Index: 693