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

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

Neuron 1985 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: 1.0846. Min Range: -1.0846

Max Act: 1.0846. Min Act: -0.0001

Data Index: 1579028 (Python Code)

Max Activating Token Index: 1015

Text #1

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.9596. Min Act: -0.0001

Data Index: 1523505 (Python Code)

Max Activating Token Index: 952

Text #2

Max Range: 1.0846. Min Range: -1.0846

Max Act: 1.0267. Min Act: -0.0001

Data Index: 1374683 (Python Code)

Max Activating Token Index: 832

Text #3

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.9759. Min Act: -0.0001

Data Index: 1628716 (Python Code)

Max Activating Token Index: 959

Text #4

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.9658. Min Act: -0.0001

Data Index: 1638648 (Python Code)

Max Activating Token Index: 388

Text #5

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.9496. Min Act: -0.0001

Data Index: 1638263 (Python Code)

Max Activating Token Index: 657

Text #6

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.8831. Min Act: -0.0001

Data Index: 1495029 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.8807. Min Act: -0.0001

Data Index: 1566777 (Python Code)

Max Activating Token Index: 804

Text #8

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.9564. Min Act: -0.0001

Data Index: 1633762 (Python Code)

Max Activating Token Index: 577

Text #9

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.8951. Min Act: -0.0001

Data Index: 1395840 (Python Code)

Max Activating Token Index: 268

Text #10

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.9196. Min Act: -0.0001

Data Index: 1445622 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.9213. Min Act: -0.0001

Data Index: 1432705 (Python Code)

Max Activating Token Index: 584

Text #12

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.9097. Min Act: -0.0001

Data Index: 1406514 (Python Code)

Max Activating Token Index: 329

Text #13

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.9612. Min Act: -0.0001

Data Index: 1402197 (Python Code)

Max Activating Token Index: 158

Text #14

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.8986. Min Act: -0.0001

Data Index: 1394346 (Python Code)

Max Activating Token Index: 817

Text #15

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.8926. Min Act: -0.0001

Data Index: 1473531 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.8551. Min Act: -0.0001

Data Index: 1427982 (Python Code)

Max Activating Token Index: 518

Text #17

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.8872. Min Act: -0.0001

Data Index: 1468900 (Python Code)

Max Activating Token Index: 639

Text #18

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.9151. Min Act: -0.0001

Data Index: 1574787 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.8412. Min Act: -0.0001

Data Index: 1571472 (Python Code)

Max Activating Token Index: 206