Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5037 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1670. Min Act: -0.0001

Data Index: 181355 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1550. Min Act: -0.0001

Data Index: 860303 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1622. Min Act: -0.0001

Data Index: 510338 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1570. Min Act: -0.0001

Data Index: 863543 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1414. Min Act: -0.0001

Data Index: 55750 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1361. Min Act: -0.0001

Data Index: 804882 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1462. Min Act: -0.0001

Data Index: 945534 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1023887 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1174838 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1254. Min Act: -0.0001

Data Index: 550408 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1358. Min Act: -0.0001

Data Index: 637107 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1307. Min Act: -0.0001

Data Index: 459423 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1088096 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1173. Min Act: -0.0001

Data Index: 551921 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1340365 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1238. Min Act: -0.0001

Data Index: 247844 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1183. Min Act: -0.0001

Data Index: 275301 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1152. Min Act: -0.0001

Data Index: 29397 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1189. Min Act: -0.0001

Data Index: 948951 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1323928 (C4 (Web Text))

Max Activating Token Index: 1007