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

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

Neuron 3791 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.4576. Min Act: -0.0001

Data Index: 1300169 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3838. Min Act: -0.0000

Data Index: 427684 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.4339. Min Act: -0.0001

Data Index: 298987 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.4661. Min Act: -0.0001

Data Index: 151401 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.4109. Min Act: -0.0001

Data Index: 825363 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.4263. Min Act: -0.0001

Data Index: 970600 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3759. Min Act: -0.0001

Data Index: 1089839 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1039602 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3544. Min Act: -0.0001

Data Index: 789520 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3774. Min Act: -0.0001

Data Index: 1262455 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3886. Min Act: -0.0000

Data Index: 84782 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3710. Min Act: -0.0001

Data Index: 558955 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3730. Min Act: -0.0001

Data Index: 836024 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1198627 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3234. Min Act: -0.0001

Data Index: 244049 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1077974 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3563. Min Act: -0.0000

Data Index: 974805 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3355. Min Act: -0.0000

Data Index: 908797 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3305. Min Act: -0.0000

Data Index: 303526 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3660. Min Act: -0.0001

Data Index: 1017622 (C4 (Web Text))

Max Activating Token Index: 950