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

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

Neuron 3699 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: 4.3224. Min Range: -4.3224

Max Act: 4.3031. Min Act: -0.0000

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 4.3224. Min Range: -4.3224

Max Act: 4.3224. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 4.3224. Min Range: -4.3224

Max Act: 4.3137. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 4.3224. Min Range: -4.3224

Max Act: 3.9027. Min Act: -0.0000

Data Index: 280806 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 4.3224. Min Range: -4.3224

Max Act: 3.9543. Min Act: -0.0000

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 4.3224. Min Range: -4.3224

Max Act: 3.4738. Min Act: -0.0000

Data Index: 293327 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 4.3224. Min Range: -4.3224

Max Act: 3.3397. Min Act: -0.0000

Data Index: 847075 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 4.3224. Min Range: -4.3224

Max Act: 3.4875. Min Act: -0.0000

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 4.3224. Min Range: -4.3224

Max Act: 3.0892. Min Act: -0.0000

Data Index: 1023659 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 4.3224. Min Range: -4.3224

Max Act: 3.0687. Min Act: -0.0000

Data Index: 364549 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 4.3224. Min Range: -4.3224

Max Act: 2.7910. Min Act: -0.0000

Data Index: 1347581 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 4.3224. Min Range: -4.3224

Max Act: 2.9190. Min Act: -0.0000

Data Index: 1576805 (Python Code)

Max Activating Token Index: 560

Text #12

Max Range: 4.3224. Min Range: -4.3224

Max Act: 2.7582. Min Act: -0.0000

Data Index: 1208928 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 4.3224. Min Range: -4.3224

Max Act: 2.6450. Min Act: -0.0000

Data Index: 237852 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 4.3224. Min Range: -4.3224

Max Act: 2.7921. Min Act: -0.0000

Data Index: 1241382 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 4.3224. Min Range: -4.3224

Max Act: 2.5112. Min Act: -0.0000

Data Index: 701476 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 4.3224. Min Range: -4.3224

Max Act: 2.6150. Min Act: -0.0000

Data Index: 81333 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 4.3224. Min Range: -4.3224

Max Act: 2.5728. Min Act: -0.0000

Data Index: 544326 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 4.3224. Min Range: -4.3224

Max Act: 2.3723. Min Act: -0.0000

Data Index: 1335691 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 4.3224. Min Range: -4.3224

Max Act: 2.4773. Min Act: -0.0000

Data Index: 885882 (C4 (Web Text))

Max Activating Token Index: 104