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

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

Neuron 3506 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1712. Min Range: -1.1712

Max Act: 1.1712. Min Act: -0.0001

Data Index: 1335828 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.1712. Min Range: -1.1712

Max Act: 1.0162. Min Act: -0.0001

Data Index: 367569 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9620. Min Act: -0.0001

Data Index: 1167095 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 1.1712. Min Range: -1.1712

Max Act: 1.0169. Min Act: -0.0001

Data Index: 805704 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9363. Min Act: -0.0001

Data Index: 178994 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9437. Min Act: -0.0001

Data Index: 448018 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9512. Min Act: -0.0001

Data Index: 240959 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9780. Min Act: -0.0001

Data Index: 759387 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9726. Min Act: -0.0001

Data Index: 963278 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9076. Min Act: -0.0001

Data Index: 35668 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8677. Min Act: -0.0001

Data Index: 208555 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8634. Min Act: -0.0001

Data Index: 558500 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8682. Min Act: -0.0001

Data Index: 1350278 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8409. Min Act: -0.0001

Data Index: 473416 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8899. Min Act: -0.0001

Data Index: 1054028 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9166. Min Act: -0.0001

Data Index: 723595 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8848. Min Act: -0.0001

Data Index: 172277 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8917. Min Act: -0.0001

Data Index: 670019 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8066. Min Act: -0.0001

Data Index: 909905 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7743. Min Act: -0.0001

Data Index: 426930 (C4 (Web Text))

Max Activating Token Index: 816