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

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

Neuron 919 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1064. Min Range: -1.1064

Max Act: 1.1064. Min Act: -0.0000

Data Index: 23716 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.9927. Min Act: -0.0000

Data Index: 838424 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8910. Min Act: -0.0000

Data Index: 949454 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8698. Min Act: -0.0000

Data Index: 975264 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1050425 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8514. Min Act: -0.0000

Data Index: 789592 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1047723 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7743. Min Act: -0.0000

Data Index: 984823 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7467. Min Act: -0.0000

Data Index: 558795 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.6950. Min Act: -0.0000

Data Index: 862065 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1045550 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1290019 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1121275 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.6969. Min Act: -0.0000

Data Index: 225762 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1219589 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.6651. Min Act: -0.0000

Data Index: 500934 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.6203. Min Act: -0.0000

Data Index: 716944 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1319281 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1141933 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.6468. Min Act: -0.0000

Data Index: 322706 (C4 (Web Text))

Max Activating Token Index: 761