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

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

Neuron 1157 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.3583. Min Act: -0.0001

Data Index: 183010 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.3384. Min Act: -0.0001

Data Index: 1433750 (Python Code)

Max Activating Token Index: 164

Text #2

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.2665. Min Act: -0.0001

Data Index: 548988 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.2295. Min Act: -0.0001

Data Index: 604396 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.1889. Min Act: -0.0001

Data Index: 714551 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0749. Min Act: -0.0001

Data Index: 950090 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0760. Min Act: -0.0001

Data Index: 826878 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0147. Min Act: -0.0001

Data Index: 1378460 (Python Code)

Max Activating Token Index: 794

Text #8

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0772. Min Act: -0.0001

Data Index: 1023483 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0428. Min Act: -0.0001

Data Index: 705103 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.1392. Min Act: -0.0001

Data Index: 1231543 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0366. Min Act: -0.0001

Data Index: 57765 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9968. Min Act: -0.0001

Data Index: 518738 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0425. Min Act: -0.0001

Data Index: 1020989 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0411. Min Act: -0.0001

Data Index: 383804 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0768. Min Act: -0.0001

Data Index: 201317 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.1041. Min Act: -0.0001

Data Index: 675726 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0278. Min Act: -0.0001

Data Index: 953932 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0579. Min Act: -0.0001

Data Index: 1632227 (Python Code)

Max Activating Token Index: 876

Text #19

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9884. Min Act: -0.0001

Data Index: 101180 (C4 (Web Text))

Max Activating Token Index: 828