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

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

Neuron 0 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: 0.1952. Min Range: -0.1952

Max Act: 0.1952. Min Act: -0.0001

Data Index: 616426 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1803. Min Act: -0.0001

Data Index: 924459 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1604. Min Act: -0.0001

Data Index: 725601 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1494. Min Act: -0.0001

Data Index: 934770 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1119918 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1237171 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1332. Min Act: -0.0001

Data Index: 480617 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1328. Min Act: -0.0001

Data Index: 540299 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1331. Min Act: -0.0001

Data Index: 666676 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1095907 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1183. Min Act: -0.0001

Data Index: 339532 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1240. Min Act: -0.0001

Data Index: 653601 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1210. Min Act: -0.0001

Data Index: 78369 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1244. Min Act: -0.0001

Data Index: 221173 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1304. Min Act: -0.0001

Data Index: 134300 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1261. Min Act: -0.0001

Data Index: 241398 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1068652 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1189. Min Act: -0.0001

Data Index: 567951 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1169. Min Act: -0.0001

Data Index: 597264 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1089. Min Act: -0.0001

Data Index: 385431 (C4 (Web Text))

Max Activating Token Index: 660