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

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

Neuron 3258 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.7133. Min Act: -0.0001

Data Index: 115078 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5274. Min Act: -0.0002

Data Index: 543075 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5254. Min Act: -0.0001

Data Index: 944430 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4992. Min Act: -0.0002

Data Index: 199462 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5542. Min Act: -0.0001

Data Index: 145882 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5583. Min Act: -0.0001

Data Index: 539838 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5096. Min Act: -0.0001

Data Index: 146973 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4629. Min Act: -0.0002

Data Index: 850093 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4831. Min Act: -0.0001

Data Index: 1071648 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4938. Min Act: -0.0002

Data Index: 85102 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4785. Min Act: -0.0001

Data Index: 1228393 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4585. Min Act: -0.0001

Data Index: 438772 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4740. Min Act: -0.0001

Data Index: 1086875 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4840. Min Act: -0.0002

Data Index: 426469 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4645. Min Act: -0.0001

Data Index: 1152797 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4834. Min Act: -0.0001

Data Index: 68986 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4781. Min Act: -0.0001

Data Index: 386239 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4457. Min Act: -0.0001

Data Index: 135923 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4564. Min Act: -0.0001

Data Index: 1343360 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4359. Min Act: -0.0002

Data Index: 195570 (C4 (Web Text))

Max Activating Token Index: 1018