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

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

Neuron 1972 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.7666. Min Act: -0.0001

Data Index: 283879 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6673. Min Act: -0.0001

Data Index: 626172 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6550. Min Act: -0.0000

Data Index: 770186 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6311. Min Act: -0.0001

Data Index: 247356 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6348. Min Act: -0.0001

Data Index: 1280343 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1309822 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5630. Min Act: -0.0000

Data Index: 186672 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6201. Min Act: -0.0000

Data Index: 143086 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5941. Min Act: -0.0000

Data Index: 971566 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5529. Min Act: -0.0000

Data Index: 653805 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5711. Min Act: -0.0000

Data Index: 66668 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5491. Min Act: -0.0000

Data Index: 278712 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5369. Min Act: -0.0000

Data Index: 791220 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5527. Min Act: -0.0001

Data Index: 70860 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5614. Min Act: -0.0001

Data Index: 877862 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5169. Min Act: -0.0001

Data Index: 572657 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5335. Min Act: -0.0001

Data Index: 312043 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5446. Min Act: -0.0000

Data Index: 557933 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5197. Min Act: -0.0000

Data Index: 837410 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5139. Min Act: -0.0001

Data Index: 1248328 (C4 (Web Text))

Max Activating Token Index: 227