Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3026 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.4645. Min Act: -0.0001

Data Index: 1302668 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3892. Min Act: -0.0001

Data Index: 1310377 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3570. Min Act: -0.0001

Data Index: 547385 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3703. Min Act: -0.0001

Data Index: 805710 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3697. Min Act: -0.0001

Data Index: 1148670 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3400. Min Act: -0.0001

Data Index: 359927 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3325. Min Act: -0.0001

Data Index: 550165 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3806. Min Act: -0.0001

Data Index: 254857 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3387. Min Act: -0.0001

Data Index: 1340174 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3372. Min Act: -0.0001

Data Index: 764189 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3200. Min Act: -0.0001

Data Index: 118361 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3567. Min Act: -0.0001

Data Index: 590440 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3334. Min Act: -0.0001

Data Index: 23468 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3404. Min Act: -0.0001

Data Index: 53871 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3456. Min Act: -0.0001

Data Index: 1061008 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3214. Min Act: -0.0001

Data Index: 840432 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3086. Min Act: -0.0001

Data Index: 334615 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3392. Min Act: -0.0001

Data Index: 703723 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3227. Min Act: -0.0001

Data Index: 891365 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3223. Min Act: -0.0001

Data Index: 620457 (C4 (Web Text))

Max Activating Token Index: 508