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

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

Neuron 3109 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3467. Min Range: -2.3467

Max Act: 2.3466. Min Act: -0.0000

Data Index: 741448 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 2.3467. Min Range: -2.3467

Max Act: 2.3467. Min Act: -0.0000

Data Index: 384570 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.8241. Min Act: -0.0000

Data Index: 561768 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 2.3467. Min Range: -2.3467

Max Act: 2.0402. Min Act: -0.0000

Data Index: 1299216 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 2.3467. Min Range: -2.3467

Max Act: 2.2541. Min Act: -0.0000

Data Index: 544829 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 2.3467. Min Range: -2.3467

Max Act: 2.3145. Min Act: -0.0001

Data Index: 1044012 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 2.3467. Min Range: -2.3467

Max Act: 2.2527. Min Act: -0.0000

Data Index: 144895 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.9076. Min Act: -0.0000

Data Index: 1184126 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.6093. Min Act: -0.0001

Data Index: 1080782 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 2.3467. Min Range: -2.3467

Max Act: 2.0416. Min Act: -0.0000

Data Index: 446501 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.7255. Min Act: -0.0000

Data Index: 116259 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.4351. Min Act: -0.0001

Data Index: 938933 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.6394. Min Act: -0.0000

Data Index: 105812 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.4607. Min Act: -0.0001

Data Index: 95826 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.7512. Min Act: -0.0000

Data Index: 510575 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.6233. Min Act: -0.0000

Data Index: 880958 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.5522. Min Act: -0.0000

Data Index: 306087 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.3893. Min Act: -0.0000

Data Index: 673202 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.4584. Min Act: -0.0000

Data Index: 1249740 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 2.3467. Min Range: -2.3467

Max Act: 1.4524. Min Act: -0.0000

Data Index: 53797 (C4 (Web Text))

Max Activating Token Index: 455