Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3994 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.9554. Min Act: -0.0001

Data Index: 1090478 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.7801. Min Act: -0.0001

Data Index: 515656 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.4471. Min Act: -0.0001

Data Index: 1242016 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.3974. Min Act: -0.0001

Data Index: 1043315 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 5.9554. Min Range: -5.9554

Max Act: 4.4359. Min Act: -0.0001

Data Index: 747134 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 5.9554. Min Range: -5.9554

Max Act: 4.4190. Min Act: -0.0001

Data Index: 1017228 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 5.9554. Min Range: -5.9554

Max Act: 4.3412. Min Act: -0.0001

Data Index: 1320211 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 5.9554. Min Range: -5.9554

Max Act: 4.1906. Min Act: -0.0001

Data Index: 273286 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 5.9554. Min Range: -5.9554

Max Act: 3.9712. Min Act: -0.0001

Data Index: 1046501 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 5.9554. Min Range: -5.9554

Max Act: 4.6279. Min Act: -0.0001

Data Index: 615670 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 5.9554. Min Range: -5.9554

Max Act: 4.7561. Min Act: -0.0001

Data Index: 859548 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 5.9554. Min Range: -5.9554

Max Act: 3.4661. Min Act: -0.0001

Data Index: 581888 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 5.9554. Min Range: -5.9554

Max Act: 3.7074. Min Act: -0.0001

Data Index: 1032377 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 5.9554. Min Range: -5.9554

Max Act: 3.5325. Min Act: -0.0001

Data Index: 214982 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 5.9554. Min Range: -5.9554

Max Act: 3.4994. Min Act: -0.0001

Data Index: 265557 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 5.9554. Min Range: -5.9554

Max Act: 3.4693. Min Act: -0.0001

Data Index: 976170 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 5.9554. Min Range: -5.9554

Max Act: 3.6208. Min Act: -0.0001

Data Index: 484840 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 5.9554. Min Range: -5.9554

Max Act: 3.4192. Min Act: -0.0001

Data Index: 506743 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 5.9554. Min Range: -5.9554

Max Act: 3.7481. Min Act: -0.0001

Data Index: 921499 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 5.9554. Min Range: -5.9554

Max Act: 3.5319. Min Act: -0.0001

Data Index: 1207636 (C4 (Web Text))

Max Activating Token Index: 60