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

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

Neuron 3953 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1705. Min Range: -1.1705

Max Act: 1.1167. Min Act: -0.0000

Data Index: 665257 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 1.1705. Min Range: -1.1705

Max Act: 1.1705. Min Act: -0.0000

Data Index: 88153 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 1.1705. Min Range: -1.1705

Max Act: 1.0443. Min Act: -0.0000

Data Index: 355072 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.9451. Min Act: -0.0000

Data Index: 435071 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.9254. Min Act: -0.0000

Data Index: 76735 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.9353. Min Act: -0.0000

Data Index: 28257 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.8257. Min Act: -0.0000

Data Index: 276023 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.9396. Min Act: -0.0000

Data Index: 969821 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.8478. Min Act: -0.0000

Data Index: 424259 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.8734. Min Act: -0.0001

Data Index: 131708 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.8691. Min Act: -0.0001

Data Index: 471709 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.7627. Min Act: -0.0000

Data Index: 764564 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.8488. Min Act: -0.0000

Data Index: 377023 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.8259. Min Act: -0.0001

Data Index: 958483 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.8517. Min Act: -0.0000

Data Index: 263326 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.7342. Min Act: -0.0000

Data Index: 575266 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.8785. Min Act: -0.0000

Data Index: 484255 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.7448. Min Act: -0.0000

Data Index: 575779 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1066489 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 1.1705. Min Range: -1.1705

Max Act: 0.8058. Min Act: -0.0000

Data Index: 182373 (C4 (Web Text))

Max Activating Token Index: 598