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

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

Neuron 3438 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0002

Data Index: 133556 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0509. Min Act: -0.0002

Data Index: 187214 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0460. Min Act: -0.0002

Data Index: 280350 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0455. Min Act: -0.0003

Data Index: 889170 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0451. Min Act: -0.0002

Data Index: 622894 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0440. Min Act: -0.0002

Data Index: 894873 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0438. Min Act: -0.0002

Data Index: 495857 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0431. Min Act: -0.0002

Data Index: 151958 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0433. Min Act: -0.0002

Data Index: 829834 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1015372 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1071860 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0413. Min Act: -0.0003

Data Index: 880235 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0422. Min Act: -0.0002

Data Index: 41035 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1058906 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0413. Min Act: -0.0002

Data Index: 977181 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1113398 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1007527 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0413. Min Act: -0.0003

Data Index: 8528 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1043539 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0417. Min Act: -0.0002

Data Index: 234693 (C4 (Web Text))

Max Activating Token Index: 351