Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1185 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.2209. Min Act: -0.0000

Data Index: 447454 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1948. Min Act: -0.0000

Data Index: 708582 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1967. Min Act: -0.0001

Data Index: 676798 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1009234 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1823. Min Act: -0.0000

Data Index: 323285 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1797. Min Act: -0.0001

Data Index: 367379 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1792. Min Act: 0.0000

Data Index: 414530 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1766. Min Act: -0.0001

Data Index: 257999 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1742. Min Act: -0.0001

Data Index: 626271 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1033828 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1714. Min Act: -0.0001

Data Index: 886490 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1661. Min Act: -0.0001

Data Index: 844031 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1293391 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1008085 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1677. Min Act: -0.0001

Data Index: 593445 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1714. Min Act: -0.0001

Data Index: 523298 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1725. Min Act: -0.0001

Data Index: 975563 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1651. Min Act: -0.0001

Data Index: 531634 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1701. Min Act: -0.0001

Data Index: 959240 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1587. Min Act: -0.0001

Data Index: 977904 (C4 (Web Text))

Max Activating Token Index: 894