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

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

Neuron 3469 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5984. Min Act: -0.0000

Data Index: 329262 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5888. Min Act: -0.0001

Data Index: 1173001 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5452. Min Act: -0.0000

Data Index: 383893 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5674. Min Act: -0.0001

Data Index: 261161 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5180. Min Act: -0.0001

Data Index: 333263 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5393. Min Act: -0.0001

Data Index: 663846 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5370. Min Act: -0.0001

Data Index: 5324 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4906. Min Act: -0.0000

Data Index: 55796 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5062. Min Act: -0.0001

Data Index: 253547 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5026. Min Act: -0.0001

Data Index: 1140305 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4824. Min Act: -0.0001

Data Index: 219753 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5060. Min Act: -0.0001

Data Index: 329995 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4887. Min Act: -0.0001

Data Index: 1249013 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4566. Min Act: -0.0000

Data Index: 896571 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4682. Min Act: -0.0001

Data Index: 1030457 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4741. Min Act: -0.0001

Data Index: 283900 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4424. Min Act: -0.0000

Data Index: 665614 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4440. Min Act: -0.0001

Data Index: 1312119 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4631. Min Act: -0.0000

Data Index: 786675 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4299. Min Act: -0.0001

Data Index: 398597 (C4 (Web Text))

Max Activating Token Index: 792