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

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

Neuron 2346 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.9839. Min Act: -0.0000

Data Index: 864594 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8727. Min Act: -0.0000

Data Index: 1148806 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8704. Min Act: -0.0000

Data Index: 913183 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.6651. Min Act: -0.0000

Data Index: 937275 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.6474. Min Act: -0.0000

Data Index: 1009438 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.7879. Min Act: -0.0000

Data Index: 1025521 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.7652. Min Act: -0.0000

Data Index: 1087440 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.4971. Min Act: -0.0000

Data Index: 20225 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.4306. Min Act: -0.0000

Data Index: 178742 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.5596. Min Act: -0.0000

Data Index: 846988 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.5348. Min Act: -0.0000

Data Index: 1044676 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.4731. Min Act: -0.0000

Data Index: 215812 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.4713. Min Act: -0.0000

Data Index: 1301395 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.6014. Min Act: -0.0000

Data Index: 783314 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.3114. Min Act: -0.0000

Data Index: 203099 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.4380. Min Act: -0.0000

Data Index: 23402 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.1337. Min Act: -0.0000

Data Index: 870844 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.5336. Min Act: -0.0000

Data Index: 603537 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.2937. Min Act: -0.0000

Data Index: 220905 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.2856. Min Act: -0.0000

Data Index: 993713 (C4 (Web Text))

Max Activating Token Index: 770