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

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

Neuron 3050 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1526. Min Range: -1.1526

Max Act: 1.1526. Min Act: -0.0001

Data Index: 1076462 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.9896. Min Act: -0.0001

Data Index: 120323 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.8638. Min Act: -0.0001

Data Index: 441314 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.8611. Min Act: -0.0001

Data Index: 1327881 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.8351. Min Act: -0.0001

Data Index: 423404 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.8016. Min Act: -0.0001

Data Index: 443168 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.7679. Min Act: -0.0001

Data Index: 1295529 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.7267. Min Act: -0.0001

Data Index: 377142 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.8285. Min Act: -0.0001

Data Index: 1287509 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.7702. Min Act: -0.0001

Data Index: 1090468 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.7417. Min Act: -0.0001

Data Index: 899701 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.7166. Min Act: -0.0001

Data Index: 1265612 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.6843. Min Act: -0.0001

Data Index: 1350685 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.7240. Min Act: -0.0001

Data Index: 336088 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.6889. Min Act: -0.0001

Data Index: 455655 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.7300. Min Act: -0.0001

Data Index: 137884 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.6932. Min Act: -0.0001

Data Index: 627261 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.6682. Min Act: -0.0001

Data Index: 1300089 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.6286. Min Act: -0.0001

Data Index: 532224 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.6622. Min Act: -0.0001

Data Index: 902285 (C4 (Web Text))

Max Activating Token Index: 1017