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

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

Neuron 1945 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2028. Min Range: -2.2028

Max Act: 2.2028. Min Act: -0.0000

Data Index: 563093 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 2.2028. Min Range: -2.2028

Max Act: 2.0228. Min Act: -0.0000

Data Index: 463856 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.9095. Min Act: -0.0000

Data Index: 1108505 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.7825. Min Act: -0.0000

Data Index: 1333892 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.7267. Min Act: -0.0000

Data Index: 311594 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.7226. Min Act: -0.0000

Data Index: 437958 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.7071. Min Act: -0.0000

Data Index: 214955 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.7079. Min Act: -0.0000

Data Index: 464544 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.5994. Min Act: -0.0000

Data Index: 91737 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.5759. Min Act: -0.0000

Data Index: 985174 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.5949. Min Act: -0.0000

Data Index: 626337 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.3860. Min Act: -0.0000

Data Index: 820016 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.5608. Min Act: -0.0000

Data Index: 392110 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.5115. Min Act: -0.0000

Data Index: 361556 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1152439 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1270847 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.2725. Min Act: -0.0000

Data Index: 797360 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.4856. Min Act: -0.0000

Data Index: 772072 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.3818. Min Act: -0.0000

Data Index: 193984 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 2.2028. Min Range: -2.2028

Max Act: 1.4950. Min Act: -0.0000

Data Index: 883401 (C4 (Web Text))

Max Activating Token Index: 465