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

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

Neuron 1883 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: 1.0598. Min Range: -1.0598

Max Act: 1.0598. Min Act: -0.0001

Data Index: 187598 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8777. Min Act: -0.0001

Data Index: 1099020 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8276. Min Act: -0.0001

Data Index: 326678 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8031. Min Act: -0.0001

Data Index: 808594 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7842. Min Act: -0.0001

Data Index: 1055776 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7921. Min Act: -0.0001

Data Index: 320733 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7683. Min Act: -0.0001

Data Index: 1142015 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7229. Min Act: -0.0001

Data Index: 1112213 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7075. Min Act: -0.0001

Data Index: 135252 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.6957. Min Act: -0.0001

Data Index: 1262634 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.6756. Min Act: -0.0001

Data Index: 167777 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.6985. Min Act: -0.0001

Data Index: 533947 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.6930. Min Act: -0.0001

Data Index: 1144725 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7123. Min Act: -0.0001

Data Index: 949576 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.6206. Min Act: -0.0001

Data Index: 951074 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7013. Min Act: -0.0001

Data Index: 608753 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.6288. Min Act: -0.0001

Data Index: 718682 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.6351. Min Act: -0.0001

Data Index: 635252 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.6270. Min Act: -0.0001

Data Index: 328037 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.6705. Min Act: -0.0001

Data Index: 264572 (C4 (Web Text))

Max Activating Token Index: 87