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

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

Neuron 5878 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1029. Min Range: -1.1029

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1115773 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.1029. Min Range: -1.1029

Max Act: 1.0184. Min Act: -0.0000

Data Index: 1088206 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 1.1029. Min Range: -1.1029

Max Act: 1.0461. Min Act: -0.0000

Data Index: 981432 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.9610. Min Act: -0.0000

Data Index: 776958 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8721. Min Act: -0.0000

Data Index: 563693 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8958. Min Act: 0.0000

Data Index: 1257463 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.7966. Min Act: -0.0000

Data Index: 501552 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8939. Min Act: -0.0000

Data Index: 893559 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8474. Min Act: -0.0000

Data Index: 594838 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8391. Min Act: 0.0000

Data Index: 1043008 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8422. Min Act: -0.0000

Data Index: 345222 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1146835 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8268. Min Act: -0.0000

Data Index: 285985 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8377. Min Act: -0.0000

Data Index: 250344 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8553. Min Act: -0.0000

Data Index: 540945 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1120919 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.7742. Min Act: -0.0000

Data Index: 36675 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.7937. Min Act: 0.0000

Data Index: 1298918 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1158325 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.7574. Min Act: 0.0000

Data Index: 128651 (C4 (Web Text))

Max Activating Token Index: 332