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

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

Neuron 3978 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.4553. Min Act: -0.0001

Data Index: 1243751 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.4478. Min Act: -0.0001

Data Index: 672742 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.4241. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3558. Min Act: -0.0001

Data Index: 96626 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3570. Min Act: -0.0001

Data Index: 951255 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3438. Min Act: -0.0001

Data Index: 1516989 (Python Code)

Max Activating Token Index: 910

Text #8

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3539. Min Act: -0.0001

Data Index: 1346655 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3532. Min Act: -0.0001

Data Index: 749299 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3384. Min Act: -0.0001

Data Index: 616540 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3655. Min Act: -0.0001

Data Index: 789996 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3304. Min Act: -0.0001

Data Index: 277647 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3319. Min Act: -0.0001

Data Index: 543744 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3291. Min Act: -0.0001

Data Index: 832582 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3360. Min Act: -0.0001

Data Index: 464670 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3291. Min Act: -0.0001

Data Index: 514062 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3202. Min Act: -0.0001

Data Index: 233367 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3371. Min Act: -0.0001

Data Index: 1242940 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.4553. Min Range: -0.4553

Max Act: 0.3233. Min Act: -0.0001

Data Index: 1189 (C4 (Web Text))

Max Activating Token Index: 427