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

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

Neuron 2698 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2357. Min Range: -1.2357

Max Act: 1.2357. Min Act: -0.0000

Data Index: 506756 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 1.2357. Min Range: -1.2357

Max Act: 1.1283. Min Act: -0.0000

Data Index: 671475 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 1.2357. Min Range: -1.2357

Max Act: 1.0640. Min Act: -0.0000

Data Index: 803247 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9764. Min Act: -0.0000

Data Index: 43978 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8293. Min Act: -0.0000

Data Index: 178769 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8620. Min Act: -0.0000

Data Index: 849575 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1248922 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7958. Min Act: -0.0000

Data Index: 407423 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1087945 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1219080 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1276553 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7854. Min Act: -0.0000

Data Index: 614124 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1327632 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9177. Min Act: -0.0000

Data Index: 832107 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7995. Min Act: -0.0000

Data Index: 501693 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1222905 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7954. Min Act: -0.0000

Data Index: 111455 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1059100 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1191051 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1314870 (C4 (Web Text))

Max Activating Token Index: 29