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

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

Neuron 3713 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1969. Min Range: -1.1969

Max Act: 1.1969. Min Act: -0.0000

Data Index: 703931 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.1969. Min Range: -1.1969

Max Act: 1.0638. Min Act: -0.0001

Data Index: 1043159 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.9200. Min Act: -0.0001

Data Index: 1308072 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.9545. Min Act: -0.0000

Data Index: 780616 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.9358. Min Act: -0.0000

Data Index: 41499 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.8244. Min Act: -0.0000

Data Index: 52888 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.8410. Min Act: -0.0000

Data Index: 9650 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.8009. Min Act: -0.0000

Data Index: 187083 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.8030. Min Act: -0.0000

Data Index: 267227 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7953. Min Act: -0.0000

Data Index: 336535 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7552. Min Act: -0.0000

Data Index: 976879 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7393. Min Act: -0.0000

Data Index: 295785 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7785. Min Act: -0.0000

Data Index: 787649 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7724. Min Act: -0.0000

Data Index: 961370 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7290. Min Act: -0.0000

Data Index: 666760 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7162. Min Act: -0.0000

Data Index: 928646 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.6746. Min Act: -0.0000

Data Index: 311159 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7460. Min Act: -0.0001

Data Index: 892372 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7537. Min Act: -0.0000

Data Index: 93584 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7269. Min Act: -0.0001

Data Index: 803078 (C4 (Web Text))

Max Activating Token Index: 781