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

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

Neuron 388 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.4472. Min Act: -0.0001

Data Index: 172097 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.5133. Min Act: -0.0001

Data Index: 929524 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.4841. Min Act: -0.0001

Data Index: 870948 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.3319. Min Act: -0.0001

Data Index: 1384335 (Python Code)

Max Activating Token Index: 77

Text #4

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.3769. Min Act: -0.0001

Data Index: 1302701 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.3705. Min Act: -0.0001

Data Index: 406991 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.4821. Min Act: -0.0001

Data Index: 779163 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.3491. Min Act: -0.0001

Data Index: 898918 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.2997. Min Act: -0.0001

Data Index: 350404 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.2659. Min Act: -0.0001

Data Index: 1524042 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.3567. Min Act: -0.0001

Data Index: 1394963 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.3011. Min Act: -0.0001

Data Index: 447193 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.3779. Min Act: -0.0001

Data Index: 227519 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.2917. Min Act: -0.0001

Data Index: 407369 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.1954. Min Act: -0.0001

Data Index: 657569 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.3650. Min Act: -0.0001

Data Index: 1387022 (Python Code)

Max Activating Token Index: 824

Text #16

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.2695. Min Act: -0.0001

Data Index: 568034 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.2754. Min Act: -0.0001

Data Index: 848875 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.2670. Min Act: -0.0001

Data Index: 126914 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.2318. Min Act: -0.0001

Data Index: 401354 (C4 (Web Text))

Max Activating Token Index: 678