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

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

Neuron 3675 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: 2.7002. Min Range: -2.7002

Max Act: 2.5921. Min Act: -0.0000

Data Index: 631575 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.7002. Min Act: -0.0000

Data Index: 131806 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.5010. Min Act: -0.0000

Data Index: 1311379 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.5516. Min Act: -0.0000

Data Index: 531930 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.5404. Min Act: -0.0000

Data Index: 924403 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.5018. Min Act: -0.0000

Data Index: 878463 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.5165. Min Act: -0.0000

Data Index: 423061 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.3828. Min Act: -0.0000

Data Index: 657848 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.3585. Min Act: -0.0000

Data Index: 754238 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.4522. Min Act: -0.0000

Data Index: 598302 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.4390. Min Act: -0.0000

Data Index: 28910 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.2630. Min Act: -0.0000

Data Index: 282667 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.3711. Min Act: -0.0000

Data Index: 1227849 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.4255. Min Act: -0.0000

Data Index: 87731 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.3992. Min Act: -0.0000

Data Index: 203045 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.2176. Min Act: -0.0000

Data Index: 451257 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.2594. Min Act: -0.0000

Data Index: 444311 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.2612. Min Act: -0.0000

Data Index: 582115 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.3456. Min Act: -0.0000

Data Index: 650779 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 2.7002. Min Range: -2.7002

Max Act: 2.2480. Min Act: -0.0000

Data Index: 721898 (C4 (Web Text))

Max Activating Token Index: 102