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

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

Neuron 2191 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: 1.6745. Min Range: -1.6745

Max Act: 1.6745. Min Act: -0.0002

Data Index: 86139 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.3790. Min Act: -0.0002

Data Index: 1346097 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.4547. Min Act: -0.0002

Data Index: 622754 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.4116. Min Act: -0.0002

Data Index: 922060 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.3651. Min Act: -0.0001

Data Index: 1303785 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.3070. Min Act: -0.0002

Data Index: 969048 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.4445. Min Act: -0.0001

Data Index: 1321973 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.1739. Min Act: -0.0001

Data Index: 894416 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2135. Min Act: -0.0002

Data Index: 1154944 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2379. Min Act: -0.0002

Data Index: 892765 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2947. Min Act: -0.0002

Data Index: 960491 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2165. Min Act: -0.0002

Data Index: 919440 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.1440. Min Act: -0.0002

Data Index: 280153 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.1366. Min Act: -0.0001

Data Index: 527942 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2564. Min Act: -0.0001

Data Index: 805905 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.1096. Min Act: -0.0002

Data Index: 580852 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2049. Min Act: -0.0001

Data Index: 1100646 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.1308. Min Act: -0.0002

Data Index: 1314901 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.0622. Min Act: -0.0002

Data Index: 1326438 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.1244. Min Act: -0.0002

Data Index: 928257 (C4 (Web Text))

Max Activating Token Index: 924