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

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

Neuron 5038 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7174. Min Range: -7.7174

Max Act: 7.7174. Min Act: -0.0000

Data Index: 764042 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 7.7174. Min Range: -7.7174

Max Act: 7.5994. Min Act: -0.0001

Data Index: 858129 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 7.7174. Min Range: -7.7174

Max Act: 6.9029. Min Act: -0.0000

Data Index: 798323 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 7.7174. Min Range: -7.7174

Max Act: 6.6998. Min Act: -0.0000

Data Index: 582525 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 7.7174. Min Range: -7.7174

Max Act: 7.0505. Min Act: -0.0001

Data Index: 9409 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 7.7174. Min Range: -7.7174

Max Act: 6.8698. Min Act: -0.0001

Data Index: 107147 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 7.7174. Min Range: -7.7174

Max Act: 6.0373. Min Act: -0.0001

Data Index: 1064776 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 7.7174. Min Range: -7.7174

Max Act: 5.9795. Min Act: -0.0000

Data Index: 161432 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 7.7174. Min Range: -7.7174

Max Act: 6.1532. Min Act: -0.0001

Data Index: 856865 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 7.7174. Min Range: -7.7174

Max Act: 5.7484. Min Act: -0.0001

Data Index: 919930 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 7.7174. Min Range: -7.7174

Max Act: 5.5210. Min Act: -0.0001

Data Index: 1154296 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 7.7174. Min Range: -7.7174

Max Act: 5.8862. Min Act: -0.0000

Data Index: 1272717 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 7.7174. Min Range: -7.7174

Max Act: 5.8135. Min Act: -0.0001

Data Index: 745143 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 7.7174. Min Range: -7.7174

Max Act: 5.2793. Min Act: -0.0001

Data Index: 309334 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 7.7174. Min Range: -7.7174

Max Act: 5.7374. Min Act: -0.0001

Data Index: 1357902 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 7.7174. Min Range: -7.7174

Max Act: 6.0775. Min Act: -0.0000

Data Index: 438670 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 7.7174. Min Range: -7.7174

Max Act: 5.4048. Min Act: -0.0001

Data Index: 32111 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 7.7174. Min Range: -7.7174

Max Act: 5.3890. Min Act: -0.0001

Data Index: 274231 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 7.7174. Min Range: -7.7174

Max Act: 5.3646. Min Act: -0.0001

Data Index: 10636 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 7.7174. Min Range: -7.7174

Max Act: 5.1411. Min Act: -0.0000

Data Index: 210069 (C4 (Web Text))

Max Activating Token Index: 523