Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4011 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.6176. Min Act: -0.0001

Data Index: 477310 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5778. Min Act: -0.0001

Data Index: 386564 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5688. Min Act: -0.0001

Data Index: 796618 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5597. Min Act: -0.0001

Data Index: 196295 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5587. Min Act: -0.0001

Data Index: 1117929 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5389. Min Act: -0.0001

Data Index: 877160 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5599. Min Act: -0.0001

Data Index: 467414 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5367. Min Act: -0.0001

Data Index: 779172 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5359. Min Act: -0.0001

Data Index: 680149 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5485. Min Act: -0.0001

Data Index: 730822 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5465. Min Act: -0.0001

Data Index: 337075 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5250. Min Act: -0.0001

Data Index: 890252 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5597. Min Act: -0.0001

Data Index: 603888 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4909. Min Act: -0.0001

Data Index: 1303005 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5747. Min Act: -0.0001

Data Index: 524634 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5524. Min Act: -0.0001

Data Index: 904077 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5177. Min Act: -0.0001

Data Index: 331488 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5140. Min Act: -0.0001

Data Index: 733905 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5496. Min Act: -0.0001

Data Index: 622008 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5346. Min Act: -0.0001

Data Index: 496118 (C4 (Web Text))

Max Activating Token Index: 547