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

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

Neuron 5516 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2438. Min Range: -3.2438

Max Act: 3.2438. Min Act: -0.0000

Data Index: 318938 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 3.2438. Min Range: -3.2438

Max Act: 2.2106. Min Act: -0.0000

Data Index: 924634 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 3.2438. Min Range: -3.2438

Max Act: 2.1920. Min Act: -0.0000

Data Index: 938718 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.9656. Min Act: -0.0000

Data Index: 1273644 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.9610. Min Act: -0.0000

Data Index: 632032 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.8136. Min Act: -0.0000

Data Index: 1015896 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.6835. Min Act: -0.0000

Data Index: 218076 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.9963. Min Act: -0.0000

Data Index: 986390 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.9930. Min Act: -0.0000

Data Index: 1283149 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.8713. Min Act: -0.0000

Data Index: 399171 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 3.2438. Min Range: -3.2438

Max Act: 2.2173. Min Act: -0.0000

Data Index: 1033507 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.9724. Min Act: -0.0000

Data Index: 334021 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.9561. Min Act: -0.0000

Data Index: 1101538 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.8361. Min Act: -0.0000

Data Index: 590011 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.9214. Min Act: -0.0000

Data Index: 1108712 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.9216. Min Act: -0.0000

Data Index: 724737 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.8076. Min Act: -0.0000

Data Index: 927480 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.9270. Min Act: -0.0000

Data Index: 125551 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.9057. Min Act: -0.0000

Data Index: 721184 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 3.2438. Min Range: -3.2438

Max Act: 1.7830. Min Act: -0.0000

Data Index: 948826 (C4 (Web Text))

Max Activating Token Index: 296