Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 203 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.7889. Min Act: -0.0000

Data Index: 157296 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6341. Min Act: -0.0000

Data Index: 1304033 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.4627. Min Act: -0.0000

Data Index: 179612 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.4414. Min Act: -0.0000

Data Index: 978151 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6441. Min Act: -0.0000

Data Index: 292030 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.4459. Min Act: -0.0000

Data Index: 375772 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.4341. Min Act: -0.0000

Data Index: 109444 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.4263. Min Act: -0.0000

Data Index: 107359 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.1887. Min Act: -0.0000

Data Index: 948062 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.3267. Min Act: -0.0000

Data Index: 433060 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.4133. Min Act: -0.0000

Data Index: 183174 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.2687. Min Act: -0.0000

Data Index: 1286050 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.3730. Min Act: -0.0000

Data Index: 812870 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.2148. Min Act: -0.0000

Data Index: 621547 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.2020. Min Act: -0.0000

Data Index: 872371 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.1779. Min Act: -0.0000

Data Index: 519183 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.1911. Min Act: -0.0000

Data Index: 27347 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.1660. Min Act: -0.0000

Data Index: 981149 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.0285. Min Act: -0.0000

Data Index: 185932 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.0142. Min Act: -0.0000

Data Index: 1291648 (C4 (Web Text))

Max Activating Token Index: 409