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

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

Neuron 3850 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: 0.3036. Min Range: -0.3036

Max Act: 0.3036. Min Act: -0.0000

Data Index: 35652 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2627. Min Act: -0.0000

Data Index: 559678 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2874. Min Act: -0.0001

Data Index: 496813 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2747. Min Act: -0.0000

Data Index: 785316 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2570. Min Act: -0.0000

Data Index: 973871 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1174051 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2699. Min Act: -0.0000

Data Index: 863802 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2391. Min Act: -0.0001

Data Index: 373743 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2921. Min Act: -0.0000

Data Index: 569809 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1060251 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2606. Min Act: -0.0000

Data Index: 907185 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2534. Min Act: -0.0000

Data Index: 333116 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2521. Min Act: -0.0001

Data Index: 424914 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2436. Min Act: -0.0001

Data Index: 121510 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2431. Min Act: -0.0000

Data Index: 668745 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1347552 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2552. Min Act: -0.0000

Data Index: 722481 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2393. Min Act: -0.0000

Data Index: 94888 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2282. Min Act: -0.0001

Data Index: 1083198 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2416. Min Act: -0.0000

Data Index: 385925 (C4 (Web Text))

Max Activating Token Index: 596