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

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

Neuron 3449 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: 0.9567. Min Range: -0.9567

Max Act: 0.9567. Min Act: -0.0002

Data Index: 132240 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8012. Min Act: -0.0001

Data Index: 138070 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8113. Min Act: -0.0001

Data Index: 74661 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8518. Min Act: -0.0002

Data Index: 1274788 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8205. Min Act: -0.0002

Data Index: 620133 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8356. Min Act: -0.0001

Data Index: 1011023 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8354. Min Act: -0.0002

Data Index: 259123 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8224. Min Act: -0.0001

Data Index: 1319474 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8146. Min Act: -0.0002

Data Index: 1356971 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7915. Min Act: -0.0001

Data Index: 210762 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7856. Min Act: -0.0002

Data Index: 394311 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8362. Min Act: -0.0001

Data Index: 661844 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8285. Min Act: -0.0002

Data Index: 102644 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8380. Min Act: -0.0001

Data Index: 5127 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8138. Min Act: -0.0001

Data Index: 1256668 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8118. Min Act: -0.0001

Data Index: 185242 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7672. Min Act: -0.0001

Data Index: 365626 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7783. Min Act: -0.0002

Data Index: 1111227 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7533. Min Act: -0.0001

Data Index: 1066491 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8611. Min Act: -0.0001

Data Index: 333197 (C4 (Web Text))

Max Activating Token Index: 670