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

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

Neuron 590 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.2214. Min Act: -0.0002

Data Index: 802714 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1690. Min Act: -0.0002

Data Index: 296797 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1735. Min Act: -0.0002

Data Index: 1298464 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1231. Min Act: -0.0002

Data Index: 40310 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1020. Min Act: -0.0002

Data Index: 1118506 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0991. Min Act: -0.0002

Data Index: 96423 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1084. Min Act: -0.0002

Data Index: 198180 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0745. Min Act: -0.0002

Data Index: 411562 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0563. Min Act: -0.0002

Data Index: 350440 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0591. Min Act: -0.0002

Data Index: 1174249 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0748. Min Act: -0.0002

Data Index: 159064 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0350. Min Act: -0.0002

Data Index: 133638 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0407. Min Act: -0.0002

Data Index: 537569 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0517. Min Act: -0.0003

Data Index: 1251568 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0475. Min Act: -0.0002

Data Index: 1344057 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0286. Min Act: -0.0002

Data Index: 9038 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0196. Min Act: -0.0002

Data Index: 887983 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0383. Min Act: -0.0002

Data Index: 96596 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0177. Min Act: -0.0002

Data Index: 1252727 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.9875. Min Act: -0.0002

Data Index: 1080171 (C4 (Web Text))

Max Activating Token Index: 373