Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2549 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1285471 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1131022 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1033. Min Act: -0.0001

Data Index: 817716 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1009. Min Act: -0.0001

Data Index: 968456 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1145868 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0907. Min Act: -0.0001

Data Index: 236363 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1331527 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0954. Min Act: -0.0001

Data Index: 598293 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0950. Min Act: -0.0001

Data Index: 90387 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0913. Min Act: -0.0001

Data Index: 50179 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0909. Min Act: -0.0001

Data Index: 191269 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1335592 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0932. Min Act: -0.0001

Data Index: 1183983 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0926. Min Act: -0.0001

Data Index: 300792 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1287701 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0917. Min Act: -0.0001

Data Index: 577054 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0952. Min Act: -0.0001

Data Index: 135337 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0954. Min Act: -0.0001

Data Index: 620677 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0942. Min Act: -0.0001

Data Index: 104935 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1086918 (C4 (Web Text))

Max Activating Token Index: 590