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

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

Neuron 4396 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: 3.2801. Min Range: -3.2801

Max Act: 3.2801. Min Act: -0.0000

Data Index: 616030 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 3.2801. Min Range: -3.2801

Max Act: 3.0846. Min Act: -0.0000

Data Index: 43589 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 3.2801. Min Range: -3.2801

Max Act: 3.0330. Min Act: -0.0000

Data Index: 335797 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 3.2801. Min Range: -3.2801

Max Act: 3.0002. Min Act: -0.0000

Data Index: 544318 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.7082. Min Act: -0.0000

Data Index: 662802 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.8040. Min Act: -0.0000

Data Index: 1227434 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.7548. Min Act: -0.0000

Data Index: 178361 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.6061. Min Act: -0.0000

Data Index: 297355 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.7149. Min Act: -0.0000

Data Index: 1310355 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.7154. Min Act: -0.0000

Data Index: 106596 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.4987. Min Act: -0.0000

Data Index: 736668 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.6426. Min Act: -0.0000

Data Index: 494507 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.1331. Min Act: -0.0000

Data Index: 1259933 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.5762. Min Act: -0.0000

Data Index: 1440396 (Python Code)

Max Activating Token Index: 785

Text #14

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.5637. Min Act: -0.0000

Data Index: 1362025 (Python Code)

Max Activating Token Index: 977

Text #15

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.7003. Min Act: -0.0000

Data Index: 1033959 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.8016. Min Act: -0.0000

Data Index: 878361 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.5455. Min Act: -0.0000

Data Index: 236914 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.4152. Min Act: -0.0000

Data Index: 894443 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 3.2801. Min Range: -3.2801

Max Act: 2.4143. Min Act: -0.0000

Data Index: 99802 (C4 (Web Text))

Max Activating Token Index: 702