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

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

Neuron 1312 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.3093. Min Act: -0.0001

Data Index: 759810 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2688. Min Act: -0.0001

Data Index: 1116219 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1321946 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2711. Min Act: -0.0001

Data Index: 1349839 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2790. Min Act: -0.0001

Data Index: 309067 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2563. Min Act: -0.0001

Data Index: 1152957 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2475. Min Act: -0.0000

Data Index: 825789 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2807. Min Act: -0.0001

Data Index: 694045 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2595. Min Act: -0.0001

Data Index: 631797 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1143186 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2704. Min Act: -0.0000

Data Index: 422879 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1211022 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2455. Min Act: -0.0001

Data Index: 90801 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2458. Min Act: -0.0000

Data Index: 268555 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2430. Min Act: -0.0001

Data Index: 801902 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1014188 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2594. Min Act: -0.0001

Data Index: 556937 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2414. Min Act: -0.0001

Data Index: 23730 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2273. Min Act: -0.0001

Data Index: 1267368 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1316437 (C4 (Web Text))

Max Activating Token Index: 732