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

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

Neuron 1997 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1761. Min Range: -2.1761

Max Act: 2.1761. Min Act: -0.0000

Data Index: 373309 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 2.1761. Min Range: -2.1761

Max Act: 2.0939. Min Act: -0.0000

Data Index: 326076 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.9164. Min Act: -0.0000

Data Index: 1350341 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.7876. Min Act: -0.0000

Data Index: 584674 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.9685. Min Act: -0.0000

Data Index: 733318 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.9206. Min Act: -0.0000

Data Index: 830154 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.8408. Min Act: -0.0000

Data Index: 1082557 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 2.1761. Min Range: -2.1761

Max Act: 2.0302. Min Act: -0.0000

Data Index: 498084 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.9214. Min Act: -0.0000

Data Index: 154688 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.8994. Min Act: -0.0000

Data Index: 1067276 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.7875. Min Act: -0.0000

Data Index: 9062 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.7548. Min Act: -0.0000

Data Index: 209554 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.7672. Min Act: -0.0000

Data Index: 125617 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.6313. Min Act: -0.0000

Data Index: 1280910 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.6944. Min Act: -0.0000

Data Index: 418434 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.7647. Min Act: -0.0000

Data Index: 661816 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.7161. Min Act: -0.0000

Data Index: 171195 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.7008. Min Act: -0.0000

Data Index: 383051 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.6842. Min Act: -0.0000

Data Index: 958838 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 2.1761. Min Range: -2.1761

Max Act: 1.6277. Min Act: -0.0000

Data Index: 950941 (C4 (Web Text))

Max Activating Token Index: 318