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

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

Neuron 2018 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6540. Min Act: -0.0000

Data Index: 958946 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4593. Min Act: 0.0000

Data Index: 165643 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4552. Min Act: -0.0000

Data Index: 165144 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1148617 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1135373 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3682. Min Act: 0.0000

Data Index: 1033393 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1294452 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3707. Min Act: -0.0000

Data Index: 63148 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3479. Min Act: -0.0000

Data Index: 215363 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3331. Min Act: -0.0000

Data Index: 263997 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3234. Min Act: -0.0000

Data Index: 868797 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1266940 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3246. Min Act: -0.0000

Data Index: 208141 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3351. Min Act: -0.0000

Data Index: 626291 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3173. Min Act: -0.0000

Data Index: 957044 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1123509 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1321674 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.2866. Min Act: 0.0000

Data Index: 1161521 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1301046 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.3032. Min Act: -0.0000

Data Index: 179310 (C4 (Web Text))

Max Activating Token Index: 311