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

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

Neuron 2194 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.7888. Min Act: -0.0000

Data Index: 809271 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 5.7888. Min Range: -5.7888

Max Act: 4.6479. Min Act: -0.0000

Data Index: 481758 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 5.7888. Min Range: -5.7888

Max Act: 4.2444. Min Act: -0.0000

Data Index: 465547 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 5.7888. Min Range: -5.7888

Max Act: 4.1048. Min Act: -0.0000

Data Index: 239497 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 5.7888. Min Range: -5.7888

Max Act: 4.0791. Min Act: -0.0000

Data Index: 383352 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.9045. Min Act: -0.0000

Data Index: 784719 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.7971. Min Act: -0.0000

Data Index: 1343158 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.8426. Min Act: -0.0000

Data Index: 1116666 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.9908. Min Act: -0.0000

Data Index: 827304 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.9215. Min Act: -0.0000

Data Index: 148973 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.7107. Min Act: -0.0000

Data Index: 1017584 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.6322. Min Act: -0.0000

Data Index: 1340756 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.3797. Min Act: -0.0000

Data Index: 1136599 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.6202. Min Act: -0.0000

Data Index: 917463 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.3741. Min Act: -0.0000

Data Index: 575864 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.2087. Min Act: -0.0000

Data Index: 146941 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.3327. Min Act: -0.0000

Data Index: 963282 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.3019. Min Act: -0.0000

Data Index: 1339149 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.3297. Min Act: -0.0000

Data Index: 454615 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 5.7888. Min Range: -5.7888

Max Act: 3.2609. Min Act: -0.0000

Data Index: 294980 (C4 (Web Text))

Max Activating Token Index: 390