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

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

Neuron 3864 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2731. Min Act: -0.0000

Data Index: 537281 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2416. Min Act: -0.0001

Data Index: 376720 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2340. Min Act: -0.0000

Data Index: 538916 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2149. Min Act: -0.0000

Data Index: 931250 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1168991 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1315516 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1899. Min Act: -0.0000

Data Index: 217710 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1690. Min Act: -0.0000

Data Index: 332270 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1776. Min Act: -0.0000

Data Index: 506435 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1748. Min Act: -0.0000

Data Index: 20378 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1980. Min Act: -0.0000

Data Index: 858339 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1592. Min Act: -0.0000

Data Index: 127954 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1616. Min Act: -0.0000

Data Index: 874467 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1508939 (Python Code)

Max Activating Token Index: 643

Text #14

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1264. Min Act: -0.0000

Data Index: 657164 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1615745 (Python Code)

Max Activating Token Index: 880

Text #16

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1266. Min Act: -0.0000

Data Index: 8402 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1316. Min Act: -0.0000

Data Index: 246166 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1410798 (Python Code)

Max Activating Token Index: 997

Text #19

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1266. Min Act: -0.0000

Data Index: 872589 (C4 (Web Text))

Max Activating Token Index: 694