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

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

Neuron 151 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: 1.2608. Min Range: -1.2608

Max Act: 1.2608. Min Act: -0.0001

Data Index: 199809 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.2608. Min Range: -1.2608

Max Act: 1.2095. Min Act: -0.0001

Data Index: 1279252 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9423. Min Act: -0.0001

Data Index: 707082 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9123. Min Act: -0.0001

Data Index: 896935 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 1.2608. Min Range: -1.2608

Max Act: 1.0515. Min Act: -0.0001

Data Index: 1271091 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9638. Min Act: -0.0001

Data Index: 1221507 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9951. Min Act: -0.0001

Data Index: 1197189 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 1.2608. Min Range: -1.2608

Max Act: 1.0584. Min Act: -0.0001

Data Index: 1167011 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.2608. Min Range: -1.2608

Max Act: 1.0570. Min Act: -0.0001

Data Index: 1101670 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.8951. Min Act: -0.0001

Data Index: 906765 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.8839. Min Act: -0.0001

Data Index: 702056 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9731. Min Act: -0.0001

Data Index: 745001 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9126. Min Act: -0.0001

Data Index: 1139337 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.8065. Min Act: -0.0001

Data Index: 116751 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.8991. Min Act: -0.0001

Data Index: 658192 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9511. Min Act: -0.0001

Data Index: 975996 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.8475. Min Act: -0.0000

Data Index: 529570 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.9038. Min Act: -0.0001

Data Index: 1066880 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.8582. Min Act: -0.0001

Data Index: 426086 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 1.2608. Min Range: -1.2608

Max Act: 0.8697. Min Act: -0.0001

Data Index: 886221 (C4 (Web Text))

Max Activating Token Index: 374