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

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

Neuron 1647 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.2677. Min Act: -0.0000

Data Index: 235386 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.2533. Min Act: -0.0000

Data Index: 746158 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.2912. Min Act: -0.0000

Data Index: 714047 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.1515. Min Act: -0.0001

Data Index: 410348 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1286944 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.2360. Min Act: -0.0000

Data Index: 1135799 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.1944. Min Act: -0.0000

Data Index: 381995 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.1392. Min Act: -0.0000

Data Index: 330742 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.0453. Min Act: -0.0000

Data Index: 564513 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.0760. Min Act: -0.0000

Data Index: 311433 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.1425. Min Act: -0.0001

Data Index: 82240 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.1045. Min Act: -0.0000

Data Index: 877359 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.1356. Min Act: -0.0000

Data Index: 299967 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.1987. Min Act: -0.0000

Data Index: 275159 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.2912. Min Range: -1.2912

Max Act: 0.9877. Min Act: -0.0000

Data Index: 284649 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.0155. Min Act: -0.0000

Data Index: 772153 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.0799. Min Act: -0.0000

Data Index: 132991 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.1071. Min Act: -0.0000

Data Index: 940556 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.1041. Min Act: -0.0000

Data Index: 333226 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 1.2912. Min Range: -1.2912

Max Act: 1.0132. Min Act: -0.0000

Data Index: 3452 (C4 (Web Text))

Max Activating Token Index: 770