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

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

Neuron 326 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.4690. Min Act: -0.0000

Data Index: 45615 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0213. Min Act: -0.0000

Data Index: 725182 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0230. Min Act: -0.0000

Data Index: 259245 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.9580. Min Act: 0.0000

Data Index: 1108606 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.9270. Min Act: -0.0000

Data Index: 377465 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.9256. Min Act: 0.0000

Data Index: 727058 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.8657. Min Act: 0.0000

Data Index: 1305290 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.9059. Min Act: 0.0000

Data Index: 157669 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.9449. Min Act: -0.0000

Data Index: 952634 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.8866. Min Act: -0.0000

Data Index: 204656 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.8801. Min Act: -0.0000

Data Index: 537299 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1255144 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.8437. Min Act: -0.0000

Data Index: 567280 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1006079 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.7577. Min Act: 0.0000

Data Index: 437553 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.7952. Min Act: 0.0000

Data Index: 742773 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.7889. Min Act: -0.0000

Data Index: 963163 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.8304. Min Act: -0.0000

Data Index: 132390 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.7787. Min Act: 0.0000

Data Index: 629034 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.7211. Min Act: -0.0000

Data Index: 865227 (C4 (Web Text))

Max Activating Token Index: 340