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

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

Neuron 3839 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.1771. Min Act: -0.0002

Data Index: 353558 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.0809. Min Act: -0.0001

Data Index: 483543 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.1021. Min Act: -0.0002

Data Index: 1147527 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9854. Min Act: -0.0002

Data Index: 427391 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.0196. Min Act: -0.0002

Data Index: 1116368 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.0072. Min Act: -0.0002

Data Index: 992804 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.0087. Min Act: -0.0001

Data Index: 161663 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9493. Min Act: -0.0002

Data Index: 458691 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.0658. Min Act: -0.0002

Data Index: 523318 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.0006. Min Act: -0.0001

Data Index: 276552 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9931. Min Act: -0.0001

Data Index: 107265 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.7923. Min Act: -0.0001

Data Index: 1301577 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9856. Min Act: -0.0002

Data Index: 937389 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9405. Min Act: -0.0001

Data Index: 1261791 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9256. Min Act: -0.0001

Data Index: 136466 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9725. Min Act: -0.0002

Data Index: 802514 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9910. Min Act: -0.0001

Data Index: 64726 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9006. Min Act: -0.0002

Data Index: 1021957 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.0326. Min Act: -0.0002

Data Index: 1163793 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9593. Min Act: -0.0002

Data Index: 128917 (C4 (Web Text))

Max Activating Token Index: 24