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

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

Neuron 3291 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9781. Min Range: -3.9781

Max Act: 3.9781. Min Act: -0.0000

Data Index: 974557 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 3.9781. Min Range: -3.9781

Max Act: 3.1468. Min Act: -0.0000

Data Index: 365179 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 3.9781. Min Range: -3.9781

Max Act: 3.0369. Min Act: -0.0000

Data Index: 492816 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.8920. Min Act: -0.0000

Data Index: 1089289 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 3.9781. Min Range: -3.9781

Max Act: 3.3300. Min Act: -0.0000

Data Index: 717017 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 3.9781. Min Range: -3.9781

Max Act: 3.1549. Min Act: -0.0000

Data Index: 645434 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.5263. Min Act: -0.0000

Data Index: 354362 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.5796. Min Act: -0.0000

Data Index: 353872 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.7871. Min Act: -0.0000

Data Index: 223332 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.4154. Min Act: -0.0000

Data Index: 192631 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.5264. Min Act: -0.0000

Data Index: 433101 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.2607. Min Act: -0.0000

Data Index: 342667 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.5118. Min Act: -0.0000

Data Index: 220240 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.4053. Min Act: -0.0000

Data Index: 44824 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.5310. Min Act: -0.0000

Data Index: 533327 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.1972. Min Act: -0.0000

Data Index: 1088289 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.3172. Min Act: -0.0000

Data Index: 726395 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.2974. Min Act: -0.0000

Data Index: 1197817 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.2832. Min Act: -0.0000

Data Index: 1015164 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 3.9781. Min Range: -3.9781

Max Act: 2.1024. Min Act: -0.0000

Data Index: 958340 (C4 (Web Text))

Max Activating Token Index: 782