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

Dataset: The Pile

Neuron 1047 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.4223. Min Act: -0.0000

Data Index: 811008 (The Pile)

Max Activating Token Index: 558

Text #1

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.9039. Min Act: -0.0000

Data Index: 1385561 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.8917. Min Act: -0.0000

Data Index: 924558 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1899398 (The Pile)

Max Activating Token Index: 955

Text #4

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.8692. Min Act: -0.0000

Data Index: 760832 (The Pile)

Max Activating Token Index: 562

Text #5

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.9192. Min Act: -0.0000

Data Index: 335351 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.8205. Min Act: -0.0000

Data Index: 957870 (The Pile)

Max Activating Token Index: 715

Text #7

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.8610. Min Act: -0.0000

Data Index: 545149 (The Pile)

Max Activating Token Index: 211

Text #8

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7990. Min Act: -0.0000

Data Index: 876987 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7944. Min Act: -0.0000

Data Index: 562560 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1704767 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7731. Min Act: -0.0000

Data Index: 242931 (The Pile)

Max Activating Token Index: 74

Text #12

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.8199. Min Act: 0.0000

Data Index: 136682 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1259392 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7568. Min Act: 0.0000

Data Index: 1974541 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1648268 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1740890 (The Pile)

Max Activating Token Index: 516

Text #17

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7329. Min Act: 0.0000

Data Index: 1066674 (The Pile)

Max Activating Token Index: 485

Text #18

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7789. Min Act: -0.0000

Data Index: 500562 (The Pile)

Max Activating Token Index: 266

Text #19

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1397175 (The Pile)

Max Activating Token Index: 404