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

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

Neuron 2258 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: 3.2470. Min Range: -3.2470

Max Act: 3.2470. Min Act: -0.0000

Data Index: 58601 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 3.2470. Min Range: -3.2470

Max Act: 3.1262. Min Act: -0.0000

Data Index: 576209 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.9171. Min Act: -0.0000

Data Index: 302129 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 3.2470. Min Range: -3.2470

Max Act: 3.1518. Min Act: -0.0000

Data Index: 824281 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.7530. Min Act: -0.0000

Data Index: 512219 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.4138. Min Act: -0.0000

Data Index: 413584 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.1831. Min Act: -0.0000

Data Index: 1334841 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.1415. Min Act: -0.0000

Data Index: 56320 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.1237. Min Act: -0.0000

Data Index: 382924 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.2150. Min Act: -0.0000

Data Index: 1163059 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.0870. Min Act: -0.0000

Data Index: 899574 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.1609. Min Act: -0.0000

Data Index: 745005 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.1547. Min Act: -0.0000

Data Index: 854101 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.1250. Min Act: -0.0000

Data Index: 504529 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.0074. Min Act: -0.0000

Data Index: 209757 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.1040. Min Act: -0.0000

Data Index: 780467 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.0950. Min Act: -0.0000

Data Index: 813410 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.0834. Min Act: -0.0000

Data Index: 873781 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.0522. Min Act: -0.0000

Data Index: 193343 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 3.2470. Min Range: -3.2470

Max Act: 2.0311. Min Act: -0.0000

Data Index: 34003 (C4 (Web Text))

Max Activating Token Index: 503