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

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

Neuron 160 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.8020. Min Range: -9.8020

Max Act: 8.9132. Min Act: -0.0000

Data Index: 1126982 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 9.8020. Min Range: -9.8020

Max Act: 9.8020. Min Act: -0.0000

Data Index: 1139721 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 9.8020. Min Range: -9.8020

Max Act: 8.5482. Min Act: -0.0000

Data Index: 1288446 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 9.8020. Min Range: -9.8020

Max Act: 9.5956. Min Act: -0.0000

Data Index: 604678 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 9.8020. Min Range: -9.8020

Max Act: 9.6114. Min Act: -0.0000

Data Index: 805502 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 9.8020. Min Range: -9.8020

Max Act: 7.6968. Min Act: -0.0000

Data Index: 214829 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 9.8020. Min Range: -9.8020

Max Act: 7.3477. Min Act: 0.0000

Data Index: 483817 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 9.8020. Min Range: -9.8020

Max Act: 7.1011. Min Act: -0.0000

Data Index: 795387 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 9.8020. Min Range: -9.8020

Max Act: 7.0078. Min Act: -0.0000

Data Index: 811335 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 9.8020. Min Range: -9.8020

Max Act: 6.2156. Min Act: -0.0000

Data Index: 164504 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 9.8020. Min Range: -9.8020

Max Act: 7.6842. Min Act: 0.0000

Data Index: 955452 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 9.8020. Min Range: -9.8020

Max Act: 6.3545. Min Act: 0.0000

Data Index: 1131791 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 9.8020. Min Range: -9.8020

Max Act: 6.2671. Min Act: 0.0000

Data Index: 506372 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 9.8020. Min Range: -9.8020

Max Act: 5.6318. Min Act: -0.0000

Data Index: 578208 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 9.8020. Min Range: -9.8020

Max Act: 5.7672. Min Act: -0.0000

Data Index: 1224598 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 9.8020. Min Range: -9.8020

Max Act: 6.6713. Min Act: -0.0000

Data Index: 1029690 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 9.8020. Min Range: -9.8020

Max Act: 6.0193. Min Act: -0.0000

Data Index: 524763 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 9.8020. Min Range: -9.8020

Max Act: 5.5470. Min Act: -0.0000

Data Index: 1273204 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 9.8020. Min Range: -9.8020

Max Act: 5.5108. Min Act: -0.0000

Data Index: 789094 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 9.8020. Min Range: -9.8020

Max Act: 5.4019. Min Act: -0.0000

Data Index: 116317 (C4 (Web Text))

Max Activating Token Index: 234