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

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

Neuron 4418 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2565. Min Act: -0.0001

Data Index: 312246 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1989. Min Act: -0.0001

Data Index: 833436 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2079. Min Act: -0.0001

Data Index: 910793 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1868. Min Act: -0.0001

Data Index: 166600 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2084. Min Act: -0.0001

Data Index: 277217 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2204. Min Act: -0.0001

Data Index: 236103 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1889. Min Act: -0.0001

Data Index: 1154810 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1690. Min Act: -0.0001

Data Index: 118541 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1922. Min Act: -0.0001

Data Index: 387415 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1836. Min Act: -0.0001

Data Index: 348307 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1600. Min Act: -0.0001

Data Index: 99199 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1072460 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1255323 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1443. Min Act: -0.0001

Data Index: 1314933 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1330. Min Act: -0.0001

Data Index: 865334 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1197. Min Act: -0.0001

Data Index: 932720 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1196. Min Act: -0.0001

Data Index: 249604 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1293. Min Act: -0.0001

Data Index: 480422 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1071705 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1253. Min Act: -0.0001

Data Index: 930884 (C4 (Web Text))

Max Activating Token Index: 644