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

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

Neuron 3118 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3481. Min Act: -0.0000

Data Index: 930382 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3362. Min Act: -0.0000

Data Index: 934173 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3239. Min Act: -0.0000

Data Index: 356732 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3076. Min Act: -0.0000

Data Index: 939388 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3182. Min Act: -0.0000

Data Index: 442864 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1244080 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2926. Min Act: -0.0000

Data Index: 552096 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3027. Min Act: -0.0000

Data Index: 724262 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2998. Min Act: -0.0000

Data Index: 588584 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2969. Min Act: -0.0000

Data Index: 23392 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1219169 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2986. Min Act: -0.0000

Data Index: 946637 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1113049 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2959. Min Act: -0.0000

Data Index: 526680 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1123768 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2621. Min Act: -0.0000

Data Index: 482027 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2716. Min Act: -0.0000

Data Index: 475649 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2683. Min Act: -0.0000

Data Index: 830230 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2595. Min Act: -0.0000

Data Index: 44925 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2695. Min Act: -0.0000

Data Index: 519281 (C4 (Web Text))

Max Activating Token Index: 59