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

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

Neuron 2431 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: 1.7075. Min Range: -1.7075

Max Act: 1.7075. Min Act: -0.0001

Data Index: 1305336 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.5012. Min Act: -0.0001

Data Index: 902683 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.5219. Min Act: -0.0001

Data Index: 195773 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.3576. Min Act: -0.0001

Data Index: 899613 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.4630. Min Act: -0.0001

Data Index: 319682 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.4159. Min Act: -0.0001

Data Index: 635114 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.5229. Min Act: -0.0001

Data Index: 465168 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.4854. Min Act: -0.0001

Data Index: 237858 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.3054. Min Act: -0.0001

Data Index: 17433 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.3801. Min Act: -0.0001

Data Index: 934895 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.2604. Min Act: -0.0001

Data Index: 335663 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.2591. Min Act: -0.0001

Data Index: 823236 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.5062. Min Act: -0.0001

Data Index: 967347 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.3150. Min Act: -0.0001

Data Index: 375642 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.2824. Min Act: -0.0001

Data Index: 1151264 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.1594. Min Act: -0.0001

Data Index: 365670 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.3334. Min Act: -0.0001

Data Index: 883968 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.3202. Min Act: -0.0001

Data Index: 740643 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.3381. Min Act: -0.0001

Data Index: 93407 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 1.7075. Min Range: -1.7075

Max Act: 1.2390. Min Act: -0.0001

Data Index: 82273 (C4 (Web Text))

Max Activating Token Index: 483