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

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

Neuron 2423 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: 0.9455. Min Range: -0.9455

Max Act: 0.9455. Min Act: -0.0000

Data Index: 704015 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.8747. Min Act: 0.0000

Data Index: 1363667 (Python Code)

Max Activating Token Index: 1019

Text #2

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.9164. Min Act: -0.0000

Data Index: 303261 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.8261. Min Act: 0.0000

Data Index: 819862 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.7349. Min Act: 0.0000

Data Index: 1547770 (Python Code)

Max Activating Token Index: 277

Text #5

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1272063 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.6536. Min Act: -0.0000

Data Index: 92488 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1345222 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.6062. Min Act: -0.0000

Data Index: 223699 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.6251. Min Act: -0.0000

Data Index: 179166 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.6238. Min Act: -0.0000

Data Index: 801973 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.5677. Min Act: -0.0000

Data Index: 584598 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1318247 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.5393. Min Act: -0.0000

Data Index: 645724 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.5487. Min Act: -0.0000

Data Index: 994717 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1185419 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.5687. Min Act: 0.0000

Data Index: 1451172 (Python Code)

Max Activating Token Index: 214

Text #17

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1160524 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.5670. Min Act: 0.0000

Data Index: 632088 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.9455. Min Range: -0.9455

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1029220 (C4 (Web Text))

Max Activating Token Index: 244