Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1200 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3197. Min Act: -0.0001

Data Index: 1311706 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2457. Min Act: -0.0001

Data Index: 739483 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2540. Min Act: -0.0001

Data Index: 544576 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2347. Min Act: -0.0001

Data Index: 1318082 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2475. Min Act: -0.0001

Data Index: 198225 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2482. Min Act: -0.0001

Data Index: 211217 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2445. Min Act: -0.0001

Data Index: 607579 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2425. Min Act: -0.0001

Data Index: 1039621 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2378. Min Act: -0.0001

Data Index: 320754 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2359. Min Act: -0.0001

Data Index: 277705 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2414. Min Act: -0.0001

Data Index: 560640 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2261. Min Act: -0.0001

Data Index: 69214 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2325. Min Act: -0.0001

Data Index: 661507 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2349. Min Act: -0.0001

Data Index: 621006 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2255. Min Act: -0.0001

Data Index: 620561 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2159. Min Act: -0.0001

Data Index: 1080865 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2192. Min Act: -0.0001

Data Index: 459742 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2188. Min Act: -0.0001

Data Index: 333907 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2182. Min Act: -0.0001

Data Index: 1033652 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2109. Min Act: -0.0001

Data Index: 270149 (C4 (Web Text))

Max Activating Token Index: 663