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

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

Neuron 1395 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.3242. Min Act: -0.0000

Data Index: 817482 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.1731. Min Act: -0.0000

Data Index: 297834 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.2379. Min Act: -0.0000

Data Index: 841746 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.2209. Min Act: -0.0000

Data Index: 346167 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.1541. Min Act: -0.0000

Data Index: 1036297 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.1505. Min Act: -0.0000

Data Index: 680088 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.0764. Min Act: -0.0000

Data Index: 341017 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.1283. Min Act: -0.0000

Data Index: 1281283 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.1228. Min Act: -0.0000

Data Index: 359659 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.0398. Min Act: -0.0000

Data Index: 576070 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.1315. Min Act: -0.0000

Data Index: 1018454 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.0925. Min Act: -0.0000

Data Index: 838094 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.0290. Min Act: -0.0000

Data Index: 336798 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.0075. Min Act: -0.0000

Data Index: 92370 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 1.3242. Min Range: -1.3242

Max Act: 1.0611. Min Act: -0.0000

Data Index: 232067 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 1.3242. Min Range: -1.3242

Max Act: 0.9900. Min Act: -0.0000

Data Index: 413549 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 1.3242. Min Range: -1.3242

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1297635 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 1.3242. Min Range: -1.3242

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1245116 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 1.3242. Min Range: -1.3242

Max Act: 0.9957. Min Act: -0.0000

Data Index: 76687 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 1.3242. Min Range: -1.3242

Max Act: 0.9623. Min Act: -0.0000

Data Index: 29160 (C4 (Web Text))

Max Activating Token Index: 560