Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2733 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.8097. Min Act: -0.0000

Data Index: 185751 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1082751 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.6238. Min Act: -0.0000

Data Index: 563587 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.6041. Min Act: -0.0000

Data Index: 862570 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1094592 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1268594 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5932. Min Act: -0.0000

Data Index: 278173 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5403. Min Act: -0.0000

Data Index: 758458 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.6237. Min Act: -0.0000

Data Index: 878022 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5718. Min Act: -0.0000

Data Index: 251039 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1295676 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5241. Min Act: -0.0000

Data Index: 973072 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5433. Min Act: -0.0000

Data Index: 55494 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5321. Min Act: -0.0000

Data Index: 660650 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1160011 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1102914 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1162821 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5062. Min Act: -0.0000

Data Index: 653655 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5183. Min Act: -0.0000

Data Index: 779288 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.8097. Min Range: -0.8097

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1080138 (C4 (Web Text))

Max Activating Token Index: 967