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

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

Neuron 1079 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.5422. Min Act: -0.0001

Data Index: 865634 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.4598. Min Act: -0.0001

Data Index: 1341726 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.4723. Min Act: -0.0001

Data Index: 589225 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.4890. Min Act: -0.0001

Data Index: 271389 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.4169. Min Act: -0.0001

Data Index: 302501 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.3266. Min Act: -0.0001

Data Index: 568845 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.3616. Min Act: -0.0001

Data Index: 721885 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.3549. Min Act: -0.0001

Data Index: 308779 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.3754. Min Act: -0.0001

Data Index: 707648 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.2265. Min Act: -0.0001

Data Index: 927507 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.2574. Min Act: -0.0001

Data Index: 1326419 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.2036. Min Act: -0.0001

Data Index: 300683 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.1722. Min Act: -0.0000

Data Index: 648658 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.2145. Min Act: -0.0001

Data Index: 697201 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.2101. Min Act: -0.0001

Data Index: 115285 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.2085. Min Act: -0.0001

Data Index: 436462 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.1686. Min Act: -0.0001

Data Index: 710904 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.1339. Min Act: -0.0001

Data Index: 611784 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.1272. Min Act: -0.0001

Data Index: 544811 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 1.5422. Min Range: -1.5422

Max Act: 1.1192. Min Act: -0.0001

Data Index: 918490 (C4 (Web Text))

Max Activating Token Index: 929