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

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

Neuron 2547 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.7220. Min Act: -0.0000

Data Index: 300527 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.5620. Min Act: -0.0000

Data Index: 449480 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.9475. Min Act: -0.0000

Data Index: 145352 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.3853. Min Act: -0.0000

Data Index: 275350 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.8208. Min Act: -0.0000

Data Index: 919159 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.7788. Min Act: -0.0000

Data Index: 1009211 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.7311. Min Act: -0.0000

Data Index: 1127625 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.4913. Min Act: -0.0000

Data Index: 628109 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.7732. Min Act: -0.0000

Data Index: 1249575 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.7434. Min Act: -0.0000

Data Index: 786831 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.4811. Min Act: -0.0000

Data Index: 837434 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.3188. Min Act: -0.0000

Data Index: 936346 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.2528. Min Act: -0.0000

Data Index: 269317 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.1769. Min Act: -0.0000

Data Index: 479487 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.1412. Min Act: -0.0000

Data Index: 395138 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.1445. Min Act: -0.0000

Data Index: 292871 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.3890. Min Act: -0.0000

Data Index: 274467 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.2136. Min Act: -0.0000

Data Index: 37002 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 4.7220. Min Range: -4.7220

Max Act: 2.9066. Min Act: -0.0000

Data Index: 797329 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 4.7220. Min Range: -4.7220

Max Act: 3.0161. Min Act: -0.0000

Data Index: 488471 (C4 (Web Text))

Max Activating Token Index: 781