Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 946 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.8232. Min Act: -0.0004

Data Index: 805535 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.8553. Min Act: -0.0004

Data Index: 105725 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7922. Min Act: -0.0004

Data Index: 1249998 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7734. Min Act: -0.0004

Data Index: 179606 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7132. Min Act: -0.0004

Data Index: 289165 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.8126. Min Act: -0.0004

Data Index: 649967 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.8511. Min Act: -0.0004

Data Index: 1124702 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7067. Min Act: -0.0004

Data Index: 373389 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6934. Min Act: -0.0004

Data Index: 77059 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.8281. Min Act: -0.0004

Data Index: 530770 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7091. Min Act: -0.0004

Data Index: 606300 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7081. Min Act: -0.0004

Data Index: 797874 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6796. Min Act: -0.0004

Data Index: 1078244 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7015. Min Act: -0.0004

Data Index: 260765 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6972. Min Act: -0.0004

Data Index: 459344 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7143. Min Act: -0.0004

Data Index: 281377 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6897. Min Act: -0.0004

Data Index: 728825 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7174. Min Act: -0.0004

Data Index: 1253243 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6532. Min Act: -0.0004

Data Index: 1131758 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6894. Min Act: -0.0004

Data Index: 244061 (C4 (Web Text))

Max Activating Token Index: 272