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

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

Neuron 4935 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5871. Min Range: -2.5871

Max Act: 2.5513. Min Act: -0.0000

Data Index: 967743 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 2.5871. Min Range: -2.5871

Max Act: 2.5871. Min Act: -0.0001

Data Index: 372509 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 2.5871. Min Range: -2.5871

Max Act: 2.5620. Min Act: -0.0000

Data Index: 578877 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 2.5871. Min Range: -2.5871

Max Act: 2.3967. Min Act: -0.0000

Data Index: 81326 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 2.5871. Min Range: -2.5871

Max Act: 2.2732. Min Act: -0.0000

Data Index: 872322 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 2.5871. Min Range: -2.5871

Max Act: 2.2492. Min Act: -0.0001

Data Index: 357534 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 2.5871. Min Range: -2.5871

Max Act: 2.0130. Min Act: -0.0000

Data Index: 773315 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 2.5871. Min Range: -2.5871

Max Act: 2.4742. Min Act: -0.0000

Data Index: 358657 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 2.5871. Min Range: -2.5871

Max Act: 2.1496. Min Act: -0.0000

Data Index: 1148237 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 2.5871. Min Range: -2.5871

Max Act: 2.0976. Min Act: -0.0000

Data Index: 15319 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 2.5871. Min Range: -2.5871

Max Act: 1.8509. Min Act: -0.0000

Data Index: 277874 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 2.5871. Min Range: -2.5871

Max Act: 1.9319. Min Act: -0.0000

Data Index: 44618 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 2.5871. Min Range: -2.5871

Max Act: 2.0431. Min Act: -0.0001

Data Index: 661484 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 2.5871. Min Range: -2.5871

Max Act: 1.9083. Min Act: -0.0000

Data Index: 221050 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 2.5871. Min Range: -2.5871

Max Act: 1.8910. Min Act: -0.0001

Data Index: 868064 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 2.5871. Min Range: -2.5871

Max Act: 1.9119. Min Act: -0.0000

Data Index: 323623 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 2.5871. Min Range: -2.5871

Max Act: 1.8915. Min Act: -0.0000

Data Index: 101111 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 2.5871. Min Range: -2.5871

Max Act: 1.8803. Min Act: -0.0000

Data Index: 252161 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 2.5871. Min Range: -2.5871

Max Act: 1.8601. Min Act: -0.0001

Data Index: 1092862 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 2.5871. Min Range: -2.5871

Max Act: 1.8523. Min Act: -0.0000

Data Index: 21514 (C4 (Web Text))

Max Activating Token Index: 991