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

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

Neuron 254 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.4118. Min Act: -0.0000

Data Index: 818647 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1011933 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3329. Min Act: -0.0000

Data Index: 820353 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3468. Min Act: -0.0000

Data Index: 685650 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3491. Min Act: -0.0000

Data Index: 251040 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3376. Min Act: -0.0000

Data Index: 897143 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1283897 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3436. Min Act: -0.0000

Data Index: 257937 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1003059 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3486. Min Act: -0.0000

Data Index: 321013 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3259. Min Act: -0.0000

Data Index: 955148 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2971. Min Act: -0.0000

Data Index: 732491 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3197. Min Act: -0.0000

Data Index: 920300 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1266496 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3300. Min Act: -0.0000

Data Index: 131088 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2772. Min Act: -0.0000

Data Index: 815567 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1170611 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1072466 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2730. Min Act: -0.0000

Data Index: 659511 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1027026 (C4 (Web Text))

Max Activating Token Index: 545