Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1600 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5994. Min Act: 0.0000

Data Index: 1355373 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1182757 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4523. Min Act: -0.0000

Data Index: 32782 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4623. Min Act: -0.0000

Data Index: 103598 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4842. Min Act: 0.0001

Data Index: 514699 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4286. Min Act: -0.0000

Data Index: 119400 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1328877 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4110. Min Act: -0.0000

Data Index: 369335 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4210. Min Act: -0.0000

Data Index: 661143 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4155. Min Act: -0.0000

Data Index: 342613 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1089520 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1335209 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4126. Min Act: -0.0000

Data Index: 202520 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3987. Min Act: -0.0000

Data Index: 828303 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3839. Min Act: -0.0000

Data Index: 447991 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3713. Min Act: -0.0000

Data Index: 749728 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3823. Min Act: -0.0000

Data Index: 943180 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3800. Min Act: -0.0000

Data Index: 326435 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3993. Min Act: -0.0000

Data Index: 471801 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3843. Min Act: -0.0000

Data Index: 885390 (C4 (Web Text))

Max Activating Token Index: 349