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

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

Neuron 3693 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.4311. Min Act: -0.0001

Data Index: 50912 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.3981. Min Act: -0.0000

Data Index: 421960 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.2769. Min Act: -0.0001

Data Index: 824028 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.2680. Min Act: -0.0001

Data Index: 486311 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.3340. Min Act: -0.0001

Data Index: 1316265 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.2463. Min Act: -0.0000

Data Index: 670210 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.2991. Min Act: -0.0001

Data Index: 1321414 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.1328. Min Act: -0.0001

Data Index: 422204 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0674. Min Act: -0.0001

Data Index: 722063 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.1450. Min Act: -0.0000

Data Index: 246835 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0990. Min Act: -0.0001

Data Index: 459072 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0333. Min Act: -0.0001

Data Index: 1145983 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0305. Min Act: -0.0001

Data Index: 227489 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1351788 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0175. Min Act: -0.0001

Data Index: 1293037 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0151. Min Act: -0.0001

Data Index: 329976 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0160. Min Act: -0.0001

Data Index: 582289 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0054. Min Act: -0.0001

Data Index: 204834 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9798. Min Act: -0.0001

Data Index: 802974 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9757. Min Act: -0.0000

Data Index: 577812 (C4 (Web Text))

Max Activating Token Index: 63