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

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

Neuron 1876 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3739. Min Act: -0.0000

Data Index: 360722 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3857. Min Act: -0.0000

Data Index: 754326 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1166692 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3961. Min Act: -0.0000

Data Index: 968049 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3537. Min Act: -0.0000

Data Index: 940379 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3886. Min Act: -0.0000

Data Index: 410093 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3381. Min Act: -0.0000

Data Index: 347835 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3167. Min Act: 0.0000

Data Index: 705856 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1490370 (Python Code)

Max Activating Token Index: 247

Text #9

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1394210 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1617550 (Python Code)

Max Activating Token Index: 444

Text #11

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3289. Min Act: -0.0000

Data Index: 988750 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3401. Min Act: -0.0000

Data Index: 209663 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2806. Min Act: -0.0000

Data Index: 667310 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3095. Min Act: -0.0000

Data Index: 524276 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3089. Min Act: -0.0000

Data Index: 236540 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3028. Min Act: -0.0000

Data Index: 196423 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3067. Min Act: -0.0000

Data Index: 273064 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1118433 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3153. Min Act: -0.0000

Data Index: 394394 (C4 (Web Text))

Max Activating Token Index: 40