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

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

Neuron 4215 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: 0.4389. Min Range: -0.4389

Max Act: 0.4389. Min Act: -0.0001

Data Index: 130606 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.4317. Min Act: -0.0001

Data Index: 330873 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3869. Min Act: -0.0001

Data Index: 558038 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3807. Min Act: -0.0001

Data Index: 905055 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3787. Min Act: -0.0001

Data Index: 416558 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3424. Min Act: -0.0001

Data Index: 359174 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3526. Min Act: -0.0001

Data Index: 1275673 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3351. Min Act: -0.0001

Data Index: 646772 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3669. Min Act: -0.0001

Data Index: 85046 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3721. Min Act: -0.0001

Data Index: 400229 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3195. Min Act: -0.0001

Data Index: 860728 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3318. Min Act: -0.0001

Data Index: 983882 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3164. Min Act: -0.0001

Data Index: 950238 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3140. Min Act: -0.0001

Data Index: 725420 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3240. Min Act: -0.0001

Data Index: 7467 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3182. Min Act: -0.0001

Data Index: 72232 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3249. Min Act: -0.0001

Data Index: 869579 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3061. Min Act: -0.0001

Data Index: 1054465 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3265. Min Act: -0.0001

Data Index: 371244 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3343. Min Act: -0.0001

Data Index: 1086955 (C4 (Web Text))

Max Activating Token Index: 418