Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1740 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.9693. Min Act: -0.0001

Data Index: 468498 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.8142. Min Act: -0.0001

Data Index: 846327 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.8847. Min Act: -0.0001

Data Index: 1047199 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.6717. Min Act: -0.0002

Data Index: 1287135 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.5211. Min Act: -0.0001

Data Index: 111186 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.6342. Min Act: -0.0002

Data Index: 67278 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.3778. Min Act: -0.0001

Data Index: 886274 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.2893. Min Act: -0.0001

Data Index: 865465 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.2249. Min Act: -0.0001

Data Index: 360784 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.1792. Min Act: -0.0001

Data Index: 274503 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.2416. Min Act: -0.0001

Data Index: 547208 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.1209. Min Act: -0.0001

Data Index: 901656 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.2450. Min Act: -0.0001

Data Index: 684039 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.1426. Min Act: -0.0002

Data Index: 778067 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.0881. Min Act: -0.0001

Data Index: 461156 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.0819. Min Act: -0.0002

Data Index: 908023 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.1100. Min Act: -0.0001

Data Index: 981232 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.1307. Min Act: -0.0002

Data Index: 725941 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.0207. Min Act: -0.0001

Data Index: 212052 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 1.9693. Min Range: -1.9693

Max Act: 1.0709. Min Act: -0.0002

Data Index: 573030 (C4 (Web Text))

Max Activating Token Index: 437