Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4507 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.1605. Min Act: -0.0002

Data Index: 928602 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0926. Min Act: -0.0002

Data Index: 383069 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0617. Min Act: -0.0002

Data Index: 108286 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0754. Min Act: -0.0002

Data Index: 1136009 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0798. Min Act: -0.0002

Data Index: 1133898 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0765. Min Act: -0.0002

Data Index: 618958 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0475. Min Act: -0.0002

Data Index: 940807 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0114. Min Act: -0.0002

Data Index: 593366 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9893. Min Act: -0.0002

Data Index: 668716 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9843. Min Act: -0.0002

Data Index: 57997 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9941. Min Act: -0.0002

Data Index: 1298556 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9732. Min Act: -0.0002

Data Index: 1218610 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9541. Min Act: -0.0002

Data Index: 910135 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9372. Min Act: -0.0002

Data Index: 146701 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9641. Min Act: -0.0002

Data Index: 223377 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9582. Min Act: -0.0002

Data Index: 1105796 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9321. Min Act: -0.0002

Data Index: 588263 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9661. Min Act: -0.0002

Data Index: 1255195 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9468. Min Act: -0.0002

Data Index: 473832 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9480. Min Act: -0.0002

Data Index: 1283174 (C4 (Web Text))

Max Activating Token Index: 796