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

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

Neuron 2806 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1165. Min Range: -1.1165

Max Act: 1.1165. Min Act: -0.0002

Data Index: 778439 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 1.1165. Min Range: -1.1165

Max Act: 1.1031. Min Act: -0.0001

Data Index: 1000331 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9021. Min Act: -0.0001

Data Index: 835901 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9382. Min Act: -0.0002

Data Index: 1005795 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.8437. Min Act: -0.0001

Data Index: 1054738 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9131. Min Act: -0.0002

Data Index: 1068387 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.8796. Min Act: -0.0002

Data Index: 1199102 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.8138. Min Act: -0.0002

Data Index: 491144 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9026. Min Act: -0.0002

Data Index: 305904 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.8431. Min Act: -0.0002

Data Index: 1339017 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9252. Min Act: -0.0002

Data Index: 996642 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.7727. Min Act: -0.0002

Data Index: 761504 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.7513. Min Act: -0.0001

Data Index: 854210 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.8883. Min Act: -0.0001

Data Index: 462833 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9066. Min Act: -0.0002

Data Index: 626025 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.7983. Min Act: -0.0002

Data Index: 430899 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.8440. Min Act: -0.0001

Data Index: 224615 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.8677. Min Act: -0.0001

Data Index: 70670 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.8752. Min Act: -0.0001

Data Index: 643323 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9145. Min Act: -0.0002

Data Index: 432300 (C4 (Web Text))

Max Activating Token Index: 838