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

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

Neuron 1115 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.9295. Min Act: 0.0000

Data Index: 1394820 (Python Code)

Max Activating Token Index: 766

Text #1

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1468783 (Python Code)

Max Activating Token Index: 96

Text #2

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7830. Min Act: 0.0001

Data Index: 1023469 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8185. Min Act: -0.0000

Data Index: 554420 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1445310 (Python Code)

Max Activating Token Index: 277

Text #5

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7232. Min Act: -0.0000

Data Index: 266863 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1427358 (Python Code)

Max Activating Token Index: 284

Text #7

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1597556 (Python Code)

Max Activating Token Index: 948

Text #8

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1382173 (Python Code)

Max Activating Token Index: 798

Text #9

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1376697 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7110. Min Act: 0.0000

Data Index: 1361355 (Python Code)

Max Activating Token Index: 724

Text #11

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6207. Min Act: -0.0000

Data Index: 139201 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1563790 (Python Code)

Max Activating Token Index: 392

Text #13

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6370. Min Act: -0.0000

Data Index: 131653 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1615247 (Python Code)

Max Activating Token Index: 891

Text #15

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6163. Min Act: -0.0000

Data Index: 496669 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1529640 (Python Code)

Max Activating Token Index: 409

Text #17

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6089. Min Act: -0.0000

Data Index: 561304 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1643862 (Python Code)

Max Activating Token Index: 149

Text #19

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5706. Min Act: -0.0000

Data Index: 1543041 (Python Code)

Max Activating Token Index: 18