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

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

Neuron 4098 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2962. Min Range: -2.2962

Max Act: 2.2962. Min Act: -0.0000

Data Index: 413140 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 2.2962. Min Range: -2.2962

Max Act: 2.1915. Min Act: -0.0000

Data Index: 304608 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 2.2962. Min Range: -2.2962

Max Act: 2.0541. Min Act: -0.0000

Data Index: 770761 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.9963. Min Act: -0.0000

Data Index: 337212 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 2.2962. Min Range: -2.2962

Max Act: 2.1896. Min Act: -0.0000

Data Index: 855482 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 2.2962. Min Range: -2.2962

Max Act: 2.0705. Min Act: -0.0000

Data Index: 1217707 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 2.2962. Min Range: -2.2962

Max Act: 2.0925. Min Act: -0.0000

Data Index: 866133 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.8586. Min Act: -0.0000

Data Index: 956635 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 2.2962. Min Range: -2.2962

Max Act: 2.0264. Min Act: -0.0000

Data Index: 268796 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.6716. Min Act: -0.0000

Data Index: 850794 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.7745. Min Act: -0.0000

Data Index: 1151404 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.7469. Min Act: -0.0000

Data Index: 189063 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.5342. Min Act: -0.0000

Data Index: 1312496 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.5157. Min Act: -0.0000

Data Index: 167336 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.6349. Min Act: -0.0000

Data Index: 770062 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.4956. Min Act: -0.0000

Data Index: 432166 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.6373. Min Act: -0.0000

Data Index: 605511 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.5552. Min Act: -0.0000

Data Index: 117700 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.6818. Min Act: -0.0000

Data Index: 972856 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 2.2962. Min Range: -2.2962

Max Act: 1.4984. Min Act: -0.0000

Data Index: 904247 (C4 (Web Text))

Max Activating Token Index: 840