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

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

Neuron 1928 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: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0003

Data Index: 578420 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0374. Min Act: -0.0003

Data Index: 1200244 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1198450 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1204347 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0350. Min Act: -0.0003

Data Index: 479704 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0350. Min Act: -0.0003

Data Index: 559022 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0357. Min Act: -0.0003

Data Index: 35542 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1001578 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0359. Min Act: -0.0003

Data Index: 350684 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1568454 (Python Code)

Max Activating Token Index: 658

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0333. Min Act: -0.0003

Data Index: 761345 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0333. Min Act: -0.0003

Data Index: 38694 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0336. Min Act: -0.0002

Data Index: 351662 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0333. Min Act: -0.0003

Data Index: 824224 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0331. Min Act: -0.0002

Data Index: 826028 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1118560 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1000671 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0334. Min Act: -0.0003

Data Index: 367405 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0322. Min Act: -0.0003

Data Index: 920003 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1183688 (C4 (Web Text))

Max Activating Token Index: 895