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

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

Neuron 3125 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.6713. Min Act: -0.0001

Data Index: 1418590 (Python Code)

Max Activating Token Index: 901

Text #1

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.6710. Min Act: -0.0001

Data Index: 1655318 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1640170 (Python Code)

Max Activating Token Index: 864

Text #3

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5326. Min Act: -0.0001

Data Index: 1610349 (Python Code)

Max Activating Token Index: 571

Text #4

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1372126 (Python Code)

Max Activating Token Index: 250

Text #5

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5006. Min Act: -0.0001

Data Index: 1484481 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1498014 (Python Code)

Max Activating Token Index: 362

Text #7

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5111. Min Act: -0.0001

Data Index: 1472985 (Python Code)

Max Activating Token Index: 238

Text #8

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1364655 (Python Code)

Max Activating Token Index: 960

Text #9

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1398580 (Python Code)

Max Activating Token Index: 290

Text #10

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4845. Min Act: -0.0001

Data Index: 1507657 (Python Code)

Max Activating Token Index: 578

Text #11

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4895. Min Act: -0.0001

Data Index: 1657099 (Python Code)

Max Activating Token Index: 338

Text #12

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5058. Min Act: -0.0001

Data Index: 1561736 (Python Code)

Max Activating Token Index: 525

Text #13

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4751. Min Act: -0.0001

Data Index: 1497465 (Python Code)

Max Activating Token Index: 745

Text #14

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1611997 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4721. Min Act: -0.0001

Data Index: 1484530 (Python Code)

Max Activating Token Index: 798

Text #16

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4845. Min Act: -0.0001

Data Index: 1594733 (Python Code)

Max Activating Token Index: 803

Text #17

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5003. Min Act: -0.0001

Data Index: 1566882 (Python Code)

Max Activating Token Index: 835

Text #18

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4545. Min Act: -0.0001

Data Index: 1630400 (Python Code)

Max Activating Token Index: 532

Text #19

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4666. Min Act: -0.0001

Data Index: 1397230 (Python Code)

Max Activating Token Index: 140