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

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

Neuron 4824 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.2541. Min Act: -0.0000

Data Index: 237887 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.1046. Min Act: 0.0000

Data Index: 1261559 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1110639 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1126669 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9830. Min Act: -0.0000

Data Index: 359890 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1201484 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9545. Min Act: -0.0000

Data Index: 136752 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0071. Min Act: -0.0000

Data Index: 748604 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9772. Min Act: -0.0000

Data Index: 358318 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9613. Min Act: -0.0000

Data Index: 415770 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9963. Min Act: -0.0000

Data Index: 224549 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9619. Min Act: -0.0000

Data Index: 613358 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9135. Min Act: -0.0000

Data Index: 110952 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9612. Min Act: 0.0000

Data Index: 332970 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9330. Min Act: -0.0000

Data Index: 841864 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9312. Min Act: -0.0000

Data Index: 506351 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9028. Min Act: -0.0000

Data Index: 257234 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.8844. Min Act: -0.0000

Data Index: 378299 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1317399 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1161813 (C4 (Web Text))

Max Activating Token Index: 142