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

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

Neuron 1986 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.5685. Min Act: -0.0001

Data Index: 549082 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.3887. Min Act: -0.0001

Data Index: 867563 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.5860. Min Act: -0.0001

Data Index: 711308 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 1.6298. Min Range: -1.6298

Max Act: 0.9507. Min Act: -0.0002

Data Index: 435343 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.3196. Min Act: -0.0001

Data Index: 90020 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.3363. Min Act: -0.0001

Data Index: 199840 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.1921. Min Act: -0.0002

Data Index: 1347152 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.2617. Min Act: -0.0001

Data Index: 825855 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.1371. Min Act: -0.0002

Data Index: 1097269 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.1643. Min Act: -0.0001

Data Index: 578170 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.1894. Min Act: -0.0001

Data Index: 1330321 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.2461. Min Act: -0.0001

Data Index: 807019 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.6298. Min Act: -0.0001

Data Index: 1112870 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.2352. Min Act: -0.0002

Data Index: 817714 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.2629. Min Act: -0.0001

Data Index: 897028 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.3804. Min Act: -0.0001

Data Index: 352321 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.1651. Min Act: -0.0001

Data Index: 831768 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.1138. Min Act: -0.0002

Data Index: 903736 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.4022. Min Act: -0.0001

Data Index: 266242 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 1.6298. Min Range: -1.6298

Max Act: 1.2179. Min Act: -0.0002

Data Index: 134025 (C4 (Web Text))

Max Activating Token Index: 1022