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

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

Neuron 1001 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.2161. Min Act: -0.0000

Data Index: 794159 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1573. Min Act: -0.0000

Data Index: 644285 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1590. Min Act: -0.0000

Data Index: 379570 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1022825 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1529. Min Act: -0.0000

Data Index: 180922 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1479. Min Act: -0.0000

Data Index: 691831 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1450. Min Act: -0.0000

Data Index: 782403 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1422. Min Act: -0.0000

Data Index: 14450 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1331. Min Act: -0.0000

Data Index: 849443 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1328. Min Act: -0.0000

Data Index: 714180 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1456. Min Act: -0.0000

Data Index: 834672 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1332. Min Act: -0.0000

Data Index: 157787 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1039324 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1281. Min Act: -0.0000

Data Index: 547275 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1290. Min Act: -0.0000

Data Index: 882582 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1330. Min Act: -0.0000

Data Index: 583275 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1305. Min Act: -0.0000

Data Index: 936522 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1223. Min Act: -0.0000

Data Index: 1056976 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1211656 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1213339 (C4 (Web Text))

Max Activating Token Index: 344