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

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

Neuron 2315 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1352662 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.5663. Min Act: -0.0001

Data Index: 163646 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4365. Min Act: -0.0001

Data Index: 325189 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.4322. Min Act: -0.0001

Data Index: 447009 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.3801. Min Act: -0.0001

Data Index: 209217 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.3584. Min Act: -0.0001

Data Index: 1009539 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.3637. Min Act: -0.0001

Data Index: 388059 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.3477. Min Act: -0.0001

Data Index: 1068907 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.3371. Min Act: -0.0001

Data Index: 832865 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.3127. Min Act: -0.0001

Data Index: 125598 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.3074. Min Act: -0.0001

Data Index: 497004 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.3275. Min Act: -0.0001

Data Index: 1067610 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.3055. Min Act: -0.0001

Data Index: 499317 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.3078. Min Act: -0.0001

Data Index: 124054 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.2807. Min Act: -0.0001

Data Index: 597843 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.2862. Min Act: -0.0001

Data Index: 395498 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.2925. Min Act: -0.0001

Data Index: 928557 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1334644 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.2849. Min Act: -0.0001

Data Index: 120616 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.6467. Min Range: -0.6467

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1329879 (C4 (Web Text))

Max Activating Token Index: 383