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

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

Neuron 4967 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1253. Min Range: -2.1253

Max Act: 2.1253. Min Act: -0.0000

Data Index: 556706 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.8333. Min Act: -0.0000

Data Index: 1188460 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.7760. Min Act: -0.0000

Data Index: 781295 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.7776. Min Act: -0.0000

Data Index: 901111 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.6670. Min Act: -0.0000

Data Index: 1124607 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.6444. Min Act: -0.0000

Data Index: 1340864 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.6175. Min Act: -0.0000

Data Index: 1091638 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.7192. Min Act: -0.0000

Data Index: 647278 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.7162. Min Act: 0.0000

Data Index: 1058334 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.5484. Min Act: -0.0000

Data Index: 1312716 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.5437. Min Act: -0.0000

Data Index: 205850 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.5309. Min Act: -0.0000

Data Index: 1326672 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.4313. Min Act: -0.0000

Data Index: 500596 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.4166. Min Act: -0.0000

Data Index: 152408 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.4169. Min Act: -0.0000

Data Index: 978528 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.4910. Min Act: -0.0000

Data Index: 231356 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.4588. Min Act: -0.0000

Data Index: 1263536 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.5511. Min Act: -0.0000

Data Index: 1219364 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.4482. Min Act: -0.0000

Data Index: 1140480 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 2.1253. Min Range: -2.1253

Max Act: 1.4403. Min Act: -0.0000

Data Index: 220616 (C4 (Web Text))

Max Activating Token Index: 377