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

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

Neuron 2458 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3668. Min Act: -0.0000

Data Index: 514726 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3769. Min Act: -0.0000

Data Index: 551816 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1045522 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3538. Min Act: -0.0001

Data Index: 103609 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3179. Min Act: -0.0000

Data Index: 573333 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3243. Min Act: -0.0000

Data Index: 582028 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3221. Min Act: -0.0000

Data Index: 791473 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3286. Min Act: -0.0000

Data Index: 609265 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3286. Min Act: -0.0001

Data Index: 1128350 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3270. Min Act: -0.0000

Data Index: 128780 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3117. Min Act: -0.0000

Data Index: 106561 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1324675 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2994. Min Act: -0.0000

Data Index: 185276 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2776. Min Act: -0.0000

Data Index: 656339 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2935. Min Act: -0.0001

Data Index: 999835 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2925. Min Act: -0.0000

Data Index: 111370 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2828. Min Act: -0.0001

Data Index: 774728 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1082219 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2646. Min Act: -0.0000

Data Index: 964817 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1188192 (C4 (Web Text))

Max Activating Token Index: 994