Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5884 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1247. Min Range: -1.1247

Max Act: 1.1247. Min Act: -0.0000

Data Index: 1240644 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 1.1247. Min Range: -1.1247

Max Act: 1.0560. Min Act: -0.0000

Data Index: 709375 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.1247. Min Range: -1.1247

Max Act: 1.0619. Min Act: -0.0000

Data Index: 505368 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 1.1247. Min Range: -1.1247

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1652363 (Python Code)

Max Activating Token Index: 360

Text #4

Max Range: 1.1247. Min Range: -1.1247

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1195825 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 1.1247. Min Range: -1.1247

Max Act: 1.0349. Min Act: -0.0000

Data Index: 54555 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.9223. Min Act: -0.0000

Data Index: 635373 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.9438. Min Act: 0.0001

Data Index: 476833 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8997. Min Act: 0.0000

Data Index: 56153 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.9435. Min Act: -0.0000

Data Index: 946885 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.9419. Min Act: -0.0000

Data Index: 719201 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8784. Min Act: -0.0000

Data Index: 206774 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8214. Min Act: -0.0000

Data Index: 275473 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8695. Min Act: -0.0000

Data Index: 35172 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1303210 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8263. Min Act: 0.0001

Data Index: 766195 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8136. Min Act: -0.0000

Data Index: 995704 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8165. Min Act: -0.0000

Data Index: 913357 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8565. Min Act: -0.0000

Data Index: 568866 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.7996. Min Act: -0.0000

Data Index: 808859 (C4 (Web Text))

Max Activating Token Index: 53