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

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

Neuron 1167 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1586112 (Python Code)

Max Activating Token Index: 896

Text #1

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1641460 (Python Code)

Max Activating Token Index: 905

Text #2

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6728. Min Act: -0.0001

Data Index: 1383920 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.7148. Min Act: -0.0001

Data Index: 1414399 (Python Code)

Max Activating Token Index: 122

Text #4

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1567723 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1383702 (Python Code)

Max Activating Token Index: 116

Text #6

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1559588 (Python Code)

Max Activating Token Index: 239

Text #7

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1456405 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1379929 (Python Code)

Max Activating Token Index: 541

Text #9

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6857. Min Act: -0.0001

Data Index: 1616661 (Python Code)

Max Activating Token Index: 443

Text #10

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1381208 (Python Code)

Max Activating Token Index: 585

Text #11

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1441815 (Python Code)

Max Activating Token Index: 948

Text #12

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1606925 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6078. Min Act: -0.0001

Data Index: 1362284 (Python Code)

Max Activating Token Index: 490

Text #14

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1427666 (Python Code)

Max Activating Token Index: 467

Text #15

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6175. Min Act: -0.0001

Data Index: 1503275 (Python Code)

Max Activating Token Index: 433

Text #16

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.6243. Min Act: -0.0001

Data Index: 1448458 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1387354 (Python Code)

Max Activating Token Index: 429

Text #18

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1376259 (Python Code)

Max Activating Token Index: 925

Text #19

Max Range: 0.9756. Min Range: -0.9756

Max Act: 0.5994. Min Act: -0.0001

Data Index: 1418279 (Python Code)

Max Activating Token Index: 555