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

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

Neuron 2674 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1351389 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0809. Min Act: -0.0002

Data Index: 568033 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0739. Min Act: -0.0002

Data Index: 772299 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0729. Min Act: -0.0002

Data Index: 471093 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1011116 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1325654 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1063941 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1092190 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0695. Min Act: -0.0002

Data Index: 730111 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0693. Min Act: -0.0002

Data Index: 986265 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0669. Min Act: -0.0002

Data Index: 691550 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0674. Min Act: -0.0002

Data Index: 107061 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1131263 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0665. Min Act: -0.0002

Data Index: 586369 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0662. Min Act: -0.0002

Data Index: 101216 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0656. Min Act: -0.0002

Data Index: 474632 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1162367 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1323804 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0636. Min Act: -0.0002

Data Index: 283449 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1239354 (C4 (Web Text))

Max Activating Token Index: 199