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

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

Neuron 165 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: 0.0947. Min Range: -0.0947

Max Act: 0.0947. Min Act: -0.0001

Data Index: 275409 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1244689 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0770. Min Act: -0.0002

Data Index: 199068 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0766. Min Act: -0.0002

Data Index: 249032 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1052599 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0756. Min Act: -0.0001

Data Index: 192076 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0725. Min Act: -0.0001

Data Index: 562252 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0748. Min Act: -0.0002

Data Index: 311466 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1290725 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0679. Min Act: -0.0001

Data Index: 357857 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0703. Min Act: -0.0001

Data Index: 639490 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0679. Min Act: -0.0002

Data Index: 703087 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0672. Min Act: -0.0001

Data Index: 826543 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0647. Min Act: -0.0001

Data Index: 969546 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1349542 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1272140 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0629. Min Act: -0.0001

Data Index: 251359 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1177212 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0640. Min Act: -0.0001

Data Index: 908002 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0694. Min Act: -0.0001

Data Index: 439928 (C4 (Web Text))

Max Activating Token Index: 463