Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3521 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.3122. Min Act: -0.0001

Data Index: 433009 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2854. Min Act: -0.0000

Data Index: 111042 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2723. Min Act: -0.0001

Data Index: 1339709 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2723. Min Act: -0.0001

Data Index: 250700 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2741. Min Act: -0.0001

Data Index: 283894 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1297943 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1179412 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1243429 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1090140 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2376. Min Act: -0.0000

Data Index: 570526 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2513. Min Act: -0.0001

Data Index: 635212 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2549. Min Act: -0.0001

Data Index: 1279258 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2459. Min Act: -0.0001

Data Index: 710892 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2476. Min Act: -0.0000

Data Index: 575438 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2279. Min Act: -0.0001

Data Index: 578249 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2342. Min Act: -0.0001

Data Index: 473761 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2279. Min Act: -0.0000

Data Index: 653873 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2290. Min Act: -0.0001

Data Index: 1284699 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2089. Min Act: -0.0000

Data Index: 572148 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2295. Min Act: -0.0001

Data Index: 401626 (C4 (Web Text))

Max Activating Token Index: 765