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

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

Neuron 3500 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.9871. Min Act: -0.0000

Data Index: 104395 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.9338. Min Act: -0.0000

Data Index: 69350 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1148388 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.8428. Min Act: -0.0000

Data Index: 331911 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7582. Min Act: -0.0000

Data Index: 29390 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7580. Min Act: -0.0000

Data Index: 534520 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1072800 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1242124 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7731. Min Act: -0.0000

Data Index: 753113 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7654. Min Act: -0.0000

Data Index: 753016 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1237387 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7602. Min Act: -0.0000

Data Index: 864292 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7350. Min Act: -0.0000

Data Index: 43978 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7531. Min Act: -0.0000

Data Index: 572051 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7507. Min Act: -0.0000

Data Index: 385110 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1133044 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1148695 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7178. Min Act: -0.0000

Data Index: 797796 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7152. Min Act: -0.0000

Data Index: 742212 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7159. Min Act: -0.0000

Data Index: 830988 (C4 (Web Text))

Max Activating Token Index: 171