Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 376 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3902. Min Act: -0.0001

Data Index: 421975 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3557. Min Act: -0.0001

Data Index: 1077415 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3347. Min Act: -0.0001

Data Index: 689588 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3706. Min Act: -0.0001

Data Index: 338659 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3944. Min Act: -0.0001

Data Index: 665882 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3572. Min Act: -0.0001

Data Index: 121545 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3274. Min Act: -0.0001

Data Index: 8277 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3619. Min Act: -0.0001

Data Index: 363858 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3161. Min Act: -0.0001

Data Index: 816777 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3957. Min Act: -0.0001

Data Index: 18348 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3413. Min Act: -0.0001

Data Index: 335277 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3494. Min Act: -0.0001

Data Index: 36029 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3341. Min Act: -0.0001

Data Index: 1194373 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3422. Min Act: -0.0001

Data Index: 299473 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3146. Min Act: -0.0001

Data Index: 1345592 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3141. Min Act: -0.0001

Data Index: 1161860 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3143. Min Act: -0.0001

Data Index: 602284 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3363. Min Act: -0.0001

Data Index: 815633 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3006. Min Act: -0.0001

Data Index: 135636 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3053. Min Act: -0.0001

Data Index: 968365 (C4 (Web Text))

Max Activating Token Index: 28