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

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

Neuron 1936 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1010157 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6890. Min Act: -0.0000

Data Index: 829464 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6485. Min Act: -0.0000

Data Index: 723013 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6062. Min Act: -0.0000

Data Index: 567114 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1100104 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5757. Min Act: -0.0000

Data Index: 663155 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1285652 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5738. Min Act: -0.0000

Data Index: 534301 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5509. Min Act: -0.0001

Data Index: 1261425 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5371. Min Act: -0.0000

Data Index: 959100 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5338. Min Act: -0.0000

Data Index: 823870 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5141. Min Act: -0.0000

Data Index: 593902 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1155557 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5077. Min Act: -0.0000

Data Index: 893636 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1115933 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5000. Min Act: -0.0000

Data Index: 511754 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5277. Min Act: -0.0000

Data Index: 748121 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5578. Min Act: -0.0000

Data Index: 46328 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1118136 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5111. Min Act: -0.0000

Data Index: 645222 (C4 (Web Text))

Max Activating Token Index: 812