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

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

Neuron 3716 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2601. Min Act: -0.0002

Data Index: 182223 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2445. Min Act: -0.0001

Data Index: 473712 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2377. Min Act: -0.0002

Data Index: 392069 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2245. Min Act: -0.0002

Data Index: 1289834 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1961. Min Act: -0.0002

Data Index: 1221161 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1937. Min Act: -0.0002

Data Index: 1191731 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1840. Min Act: -0.0001

Data Index: 883316 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1963. Min Act: -0.0002

Data Index: 788881 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1859. Min Act: -0.0001

Data Index: 1168606 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1992. Min Act: -0.0001

Data Index: 1119144 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1824. Min Act: -0.0001

Data Index: 1087494 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1856. Min Act: -0.0001

Data Index: 1163963 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1916. Min Act: -0.0002

Data Index: 1067461 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1772. Min Act: -0.0002

Data Index: 955210 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1779. Min Act: -0.0001

Data Index: 842545 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1892. Min Act: -0.0002

Data Index: 656188 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1898. Min Act: -0.0002

Data Index: 900003 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1801. Min Act: -0.0001

Data Index: 196486 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1696. Min Act: -0.0002

Data Index: 1245376 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1841. Min Act: -0.0001

Data Index: 1061116 (C4 (Web Text))

Max Activating Token Index: 572