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

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

Neuron 3034 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.2612. Min Act: -0.0001

Data Index: 804119 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.2537. Min Act: -0.0001

Data Index: 388378 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1856. Min Act: -0.0000

Data Index: 640475 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.2225. Min Act: -0.0001

Data Index: 503924 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.2091. Min Act: -0.0000

Data Index: 530168 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1998. Min Act: -0.0001

Data Index: 700668 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.2163. Min Act: -0.0000

Data Index: 544670 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1987. Min Act: -0.0000

Data Index: 490495 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.2038. Min Act: -0.0000

Data Index: 599659 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1965. Min Act: -0.0000

Data Index: 716134 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1864. Min Act: -0.0001

Data Index: 537542 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1980. Min Act: -0.0001

Data Index: 138192 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1763. Min Act: -0.0001

Data Index: 927117 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1283401 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1890. Min Act: -0.0001

Data Index: 764933 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1168762 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1817. Min Act: -0.0001

Data Index: 824847 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1898. Min Act: -0.0000

Data Index: 396181 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1293651 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.2612. Min Range: -0.2612

Max Act: 0.1876. Min Act: -0.0001

Data Index: 1357891 (C4 (Web Text))

Max Activating Token Index: 290