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

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

Neuron 847 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.8234. Min Act: -0.0001

Data Index: 1093429 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.8158. Min Act: -0.0001

Data Index: 1279812 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7845. Min Act: -0.0001

Data Index: 185788 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7937. Min Act: -0.0001

Data Index: 801690 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7335. Min Act: -0.0001

Data Index: 683197 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6444. Min Act: -0.0001

Data Index: 1168491 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7524. Min Act: -0.0001

Data Index: 700567 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7588. Min Act: -0.0001

Data Index: 579297 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7421. Min Act: -0.0001

Data Index: 648409 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7441. Min Act: -0.0001

Data Index: 395463 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7187. Min Act: -0.0001

Data Index: 552835 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7344. Min Act: -0.0001

Data Index: 824968 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6861. Min Act: -0.0001

Data Index: 609654 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6860. Min Act: -0.0001

Data Index: 486348 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6466. Min Act: -0.0001

Data Index: 1245748 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7409. Min Act: -0.0001

Data Index: 248805 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6816. Min Act: -0.0001

Data Index: 732018 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6594. Min Act: -0.0001

Data Index: 6663 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6894. Min Act: -0.0001

Data Index: 1039312 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6259. Min Act: -0.0001

Data Index: 392450 (C4 (Web Text))

Max Activating Token Index: 944