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

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

Neuron 1150 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2642. Min Act: -0.0001

Data Index: 1007711 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2626. Min Act: -0.0001

Data Index: 792541 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2392. Min Act: -0.0001

Data Index: 1143720 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2417. Min Act: -0.0001

Data Index: 116782 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2399. Min Act: -0.0001

Data Index: 1071981 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2398. Min Act: -0.0001

Data Index: 693748 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2490. Min Act: -0.0001

Data Index: 1265078 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2392. Min Act: -0.0001

Data Index: 754326 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2397. Min Act: -0.0001

Data Index: 688549 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2434. Min Act: -0.0001

Data Index: 616520 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2188. Min Act: -0.0001

Data Index: 1203240 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1204557 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2290. Min Act: -0.0001

Data Index: 956479 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2200. Min Act: -0.0001

Data Index: 241341 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1086875 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2330. Min Act: -0.0001

Data Index: 857557 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1556402 (Python Code)

Max Activating Token Index: 597

Text #17

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2146. Min Act: -0.0001

Data Index: 383330 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2380. Min Act: -0.0001

Data Index: 463850 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1248538 (C4 (Web Text))

Max Activating Token Index: 823