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

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

Neuron 3033 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: 0.3968. Min Range: -0.3968

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1075387 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3783. Min Act: -0.0000

Data Index: 241075 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3621. Min Act: -0.0000

Data Index: 887309 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3235. Min Act: -0.0000

Data Index: 759114 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1007157 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1357482 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1089843 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2828. Min Act: -0.0000

Data Index: 27592 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2806. Min Act: -0.0000

Data Index: 953597 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1519617 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2780. Min Act: -0.0000

Data Index: 582197 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1334453 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1154796 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2838. Min Act: -0.0000

Data Index: 635955 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2767. Min Act: -0.0000

Data Index: 603916 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2456. Min Act: -0.0000

Data Index: 695273 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1482809 (Python Code)

Max Activating Token Index: 676

Text #17

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2494. Min Act: -0.0000

Data Index: 777275 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2509. Min Act: -0.0000

Data Index: 3526 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2599. Min Act: -0.0000

Data Index: 861785 (C4 (Web Text))

Max Activating Token Index: 525