Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6062 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4561. Min Range: -2.4561

Max Act: 2.1564. Min Act: -0.0000

Data Index: 1049217 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 2.4561. Min Range: -2.4561

Max Act: 2.4561. Min Act: -0.0001

Data Index: 136344 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.8051. Min Act: -0.0000

Data Index: 949064 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 2.4561. Min Range: -2.4561

Max Act: 2.0811. Min Act: -0.0000

Data Index: 1203506 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.9938. Min Act: -0.0000

Data Index: 203588 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.9636. Min Act: -0.0000

Data Index: 70075 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 2.4561. Min Range: -2.4561

Max Act: 2.0821. Min Act: -0.0000

Data Index: 1217796 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 2.4561. Min Range: -2.4561

Max Act: 2.0409. Min Act: -0.0001

Data Index: 307427 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 2.4561. Min Range: -2.4561

Max Act: 2.1521. Min Act: -0.0000

Data Index: 135155 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 2.4561. Min Range: -2.4561

Max Act: 2.0126. Min Act: -0.0000

Data Index: 1120621 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 2.4561. Min Range: -2.4561

Max Act: 2.0907. Min Act: -0.0000

Data Index: 1242994 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 2.4561. Min Range: -2.4561

Max Act: 2.0348. Min Act: -0.0001

Data Index: 224971 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.9099. Min Act: -0.0000

Data Index: 537628 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.8014. Min Act: -0.0000

Data Index: 562293 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 2.4561. Min Range: -2.4561

Max Act: 2.2543. Min Act: -0.0000

Data Index: 810141 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.8904. Min Act: -0.0000

Data Index: 839992 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.9191. Min Act: -0.0001

Data Index: 540032 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.8465. Min Act: -0.0001

Data Index: 26436 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.7848. Min Act: -0.0000

Data Index: 206618 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.7496. Min Act: -0.0000

Data Index: 1227632 (C4 (Web Text))

Max Activating Token Index: 865