Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2877 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4634. Min Range: -2.4634

Max Act: 2.4634. Min Act: -0.0000

Data Index: 1109934 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 2.4634. Min Range: -2.4634

Max Act: 2.4465. Min Act: -0.0000

Data Index: 712892 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 2.4634. Min Range: -2.4634

Max Act: 2.2936. Min Act: -0.0000

Data Index: 671120 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.8005. Min Act: -0.0000

Data Index: 318295 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.9554. Min Act: 0.0000

Data Index: 1296507 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.7102. Min Act: -0.0000

Data Index: 880328 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.5289. Min Act: 0.0001

Data Index: 1441594 (Python Code)

Max Activating Token Index: 264

Text #7

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.6268. Min Act: -0.0000

Data Index: 3605 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.5922. Min Act: -0.0000

Data Index: 580559 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.4973. Min Act: -0.0000

Data Index: 1201297 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.5352. Min Act: -0.0000

Data Index: 669329 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.5185. Min Act: -0.0000

Data Index: 1537883 (Python Code)

Max Activating Token Index: 466

Text #12

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.5072. Min Act: 0.0000

Data Index: 1439614 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.5901. Min Act: 0.0001

Data Index: 1642219 (Python Code)

Max Activating Token Index: 959

Text #14

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.4945. Min Act: 0.0001

Data Index: 1385103 (Python Code)

Max Activating Token Index: 127

Text #15

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.4780. Min Act: -0.0000

Data Index: 821702 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.4428. Min Act: -0.0000

Data Index: 468143 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.4217. Min Act: -0.0000

Data Index: 719801 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.3071. Min Act: -0.0000

Data Index: 898246 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 2.4634. Min Range: -2.4634

Max Act: 1.4892. Min Act: -0.0000

Data Index: 1499815 (Python Code)

Max Activating Token Index: 875