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

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

Neuron 3301 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: 3.4132. Min Range: -3.4132

Max Act: 3.4132. Min Act: -0.0000

Data Index: 164865 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.9960. Min Act: -0.0000

Data Index: 911737 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 3.4132. Min Range: -3.4132

Max Act: 3.1221. Min Act: -0.0000

Data Index: 1228223 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.7656. Min Act: -0.0000

Data Index: 932562 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.8397. Min Act: -0.0000

Data Index: 1328495 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.5756. Min Act: -0.0000

Data Index: 368168 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.6986. Min Act: -0.0000

Data Index: 1104353 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.8145. Min Act: -0.0000

Data Index: 21642 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.6856. Min Act: -0.0000

Data Index: 449209 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.6814. Min Act: -0.0000

Data Index: 122983 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.7911. Min Act: -0.0000

Data Index: 949511 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.5263. Min Act: -0.0000

Data Index: 1089776 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.6115. Min Act: -0.0000

Data Index: 17664 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.4633. Min Act: -0.0000

Data Index: 578811 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.5877. Min Act: -0.0000

Data Index: 1243739 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.5324. Min Act: -0.0000

Data Index: 617298 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.6842. Min Act: -0.0000

Data Index: 1353005 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.5099. Min Act: -0.0000

Data Index: 1325449 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.4647. Min Act: -0.0000

Data Index: 1325163 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 3.4132. Min Range: -3.4132

Max Act: 2.4489. Min Act: -0.0000

Data Index: 555091 (C4 (Web Text))

Max Activating Token Index: 370