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

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

Neuron 909 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: 1.0385. Min Range: -1.0385

Max Act: 1.0385. Min Act: -0.0000

Data Index: 784197 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.9015. Min Act: -0.0000

Data Index: 736791 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7292. Min Act: -0.0000

Data Index: 504189 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6740. Min Act: -0.0000

Data Index: 822577 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6670. Min Act: 0.0000

Data Index: 515784 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6545. Min Act: 0.0000

Data Index: 1153315 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.5978. Min Act: -0.0000

Data Index: 750167 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6221. Min Act: -0.0000

Data Index: 805051 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.5253. Min Act: -0.0000

Data Index: 778905 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1532 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.5044. Min Act: -0.0000

Data Index: 872310 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.4983. Min Act: -0.0000

Data Index: 920494 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.4891. Min Act: -0.0000

Data Index: 44305 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.4676. Min Act: -0.0000

Data Index: 762768 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.5386. Min Act: -0.0000

Data Index: 569167 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.4817. Min Act: 0.0000

Data Index: 1031637 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.4516. Min Act: -0.0000

Data Index: 428955 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.4628. Min Act: -0.0000

Data Index: 801635 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1108923 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.4771. Min Act: 0.0000

Data Index: 849575 (C4 (Web Text))

Max Activating Token Index: 64