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

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

Neuron 3058 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: 0.3235. Min Range: -0.3235

Max Act: 0.3235. Min Act: -0.0001

Data Index: 1626720 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1590034 (Python Code)

Max Activating Token Index: 900

Text #2

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2147. Min Act: -0.0001

Data Index: 1374203 (Python Code)

Max Activating Token Index: 295

Text #3

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2184. Min Act: -0.0001

Data Index: 1390507 (Python Code)

Max Activating Token Index: 317

Text #4

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2001. Min Act: -0.0001

Data Index: 102959 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1963. Min Act: -0.0001

Data Index: 927360 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1067724 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1827. Min Act: -0.0001

Data Index: 431059 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1856. Min Act: -0.0001

Data Index: 1210573 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1916. Min Act: -0.0001

Data Index: 955656 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2024. Min Act: -0.0001

Data Index: 758438 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1814. Min Act: -0.0001

Data Index: 793231 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1831. Min Act: -0.0001

Data Index: 174640 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1698. Min Act: -0.0001

Data Index: 478826 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1278271 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1803. Min Act: -0.0001

Data Index: 693023 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1604. Min Act: -0.0001

Data Index: 746063 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1661. Min Act: -0.0001

Data Index: 481058 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1654. Min Act: -0.0000

Data Index: 879565 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.1711. Min Act: -0.0001

Data Index: 897049 (C4 (Web Text))

Max Activating Token Index: 57