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

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

Neuron 499 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1461630 (Python Code)

Max Activating Token Index: 432

Text #1

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3335. Min Act: -0.0000

Data Index: 753286 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1377117 (Python Code)

Max Activating Token Index: 548

Text #3

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1128938 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3137. Min Act: -0.0000

Data Index: 354918 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3172. Min Act: -0.0000

Data Index: 328952 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2998. Min Act: -0.0000

Data Index: 212003 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1438860 (Python Code)

Max Activating Token Index: 157

Text #8

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2999. Min Act: -0.0000

Data Index: 718891 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2935. Min Act: -0.0000

Data Index: 607874 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2910. Min Act: -0.0000

Data Index: 266482 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1054900 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2820. Min Act: -0.0000

Data Index: 549926 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2890. Min Act: -0.0000

Data Index: 404511 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2885. Min Act: -0.0000

Data Index: 219661 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2856. Min Act: -0.0000

Data Index: 910619 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1045251 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2944. Min Act: -0.0000

Data Index: 741085 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2777. Min Act: -0.0000

Data Index: 419517 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2743. Min Act: -0.0000

Data Index: 645754 (C4 (Web Text))

Max Activating Token Index: 434