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

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

Neuron 288 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: 0.3322. Min Range: -0.3322

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1146722 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2970. Min Act: -0.0001

Data Index: 149356 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1131733 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2894. Min Act: -0.0001

Data Index: 1119976 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2753. Min Act: -0.0000

Data Index: 323108 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2891. Min Act: -0.0000

Data Index: 723975 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2597. Min Act: -0.0000

Data Index: 70332 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2556. Min Act: -0.0000

Data Index: 534739 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2447. Min Act: -0.0000

Data Index: 655784 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1250169 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2325. Min Act: -0.0000

Data Index: 340150 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1156522 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2154. Min Act: -0.0000

Data Index: 261248 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2201. Min Act: -0.0000

Data Index: 658918 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2311. Min Act: -0.0000

Data Index: 396421 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2546. Min Act: -0.0001

Data Index: 1207572 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1353820 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2156. Min Act: -0.0000

Data Index: 279973 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1143803 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.3322. Min Range: -0.3322

Max Act: 0.2041. Min Act: -0.0001

Data Index: 18890 (C4 (Web Text))

Max Activating Token Index: 915