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

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

Neuron 1267 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2729. Min Act: -0.0001

Data Index: 451148 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2726. Min Act: -0.0001

Data Index: 951000 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2780. Min Act: -0.0001

Data Index: 1329755 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2486. Min Act: -0.0000

Data Index: 439813 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2623. Min Act: -0.0001

Data Index: 473952 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2631. Min Act: -0.0001

Data Index: 683888 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2545. Min Act: -0.0001

Data Index: 691182 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2569. Min Act: -0.0001

Data Index: 1037182 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2678. Min Act: -0.0001

Data Index: 958805 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2519. Min Act: -0.0001

Data Index: 939439 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2397. Min Act: -0.0001

Data Index: 1254261 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1323371 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2412. Min Act: -0.0001

Data Index: 162849 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2400. Min Act: -0.0000

Data Index: 958527 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1073454 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2142. Min Act: -0.0001

Data Index: 298087 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2296. Min Act: -0.0001

Data Index: 351144 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2379. Min Act: -0.0001

Data Index: 1036775 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2715. Min Act: -0.0001

Data Index: 1114475 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2189. Min Act: -0.0001

Data Index: 370506 (C4 (Web Text))

Max Activating Token Index: 130