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

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

Neuron 901 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: 1.5620. Min Range: -1.5620

Max Act: 1.5620. Min Act: -0.0000

Data Index: 131743 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.5272. Min Act: -0.0000

Data Index: 1279451 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.3858. Min Act: -0.0000

Data Index: 195792 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.3163. Min Act: -0.0000

Data Index: 1513867 (Python Code)

Max Activating Token Index: 435

Text #4

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.3772. Min Act: -0.0000

Data Index: 1634202 (Python Code)

Max Activating Token Index: 738

Text #5

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1116883 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.4588. Min Act: -0.0000

Data Index: 1560343 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.2798. Min Act: -0.0000

Data Index: 1612348 (Python Code)

Max Activating Token Index: 932

Text #8

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.2599. Min Act: -0.0000

Data Index: 66998 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.2409. Min Act: -0.0000

Data Index: 154261 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1156778 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.2919. Min Act: -0.0000

Data Index: 928592 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.2081. Min Act: -0.0000

Data Index: 897262 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.1562. Min Act: -0.0000

Data Index: 930581 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.1444. Min Act: -0.0000

Data Index: 297609 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.1488. Min Act: -0.0000

Data Index: 970530 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.1411. Min Act: -0.0000

Data Index: 774101 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.0820. Min Act: -0.0000

Data Index: 894668 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1585658 (Python Code)

Max Activating Token Index: 342

Text #19

Max Range: 1.5620. Min Range: -1.5620

Max Act: 1.0385. Min Act: -0.0000

Data Index: 1240833 (C4 (Web Text))

Max Activating Token Index: 44