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

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

Neuron 4701 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1169752 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.7121. Min Act: -0.0000

Data Index: 909489 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5186. Min Act: -0.0000

Data Index: 387525 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5188. Min Act: -0.0000

Data Index: 455095 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1028064 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4920. Min Act: -0.0000

Data Index: 31287 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4956. Min Act: -0.0000

Data Index: 945236 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4726. Min Act: -0.0000

Data Index: 918798 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4663. Min Act: 0.0000

Data Index: 1258269 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4767. Min Act: -0.0000

Data Index: 961617 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1212038 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4671. Min Act: -0.0000

Data Index: 457514 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4999. Min Act: -0.0000

Data Index: 179757 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1309609 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4460. Min Act: -0.0000

Data Index: 280478 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1558573 (Python Code)

Max Activating Token Index: 404

Text #16

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1574826 (Python Code)

Max Activating Token Index: 262

Text #17

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4360. Min Act: -0.0000

Data Index: 294638 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1602575 (Python Code)

Max Activating Token Index: 318

Text #19

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4642. Min Act: -0.0000

Data Index: 220425 (C4 (Web Text))

Max Activating Token Index: 937