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

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

Neuron 5957 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2887. Min Range: -3.2887

Max Act: 3.2887. Min Act: -0.0000

Data Index: 1296861 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.6935. Min Act: -0.0000

Data Index: 240109 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.6511. Min Act: -0.0000

Data Index: 118655 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.3882. Min Act: -0.0000

Data Index: 567543 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.4037. Min Act: -0.0000

Data Index: 984381 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.3775. Min Act: -0.0000

Data Index: 696876 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.4974. Min Act: -0.0000

Data Index: 1120883 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.4123. Min Act: -0.0000

Data Index: 289825 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.4117. Min Act: -0.0000

Data Index: 440933 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.3935. Min Act: -0.0000

Data Index: 226193 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.2387. Min Act: -0.0000

Data Index: 979112 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.2048. Min Act: -0.0000

Data Index: 395253 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.2899. Min Act: -0.0000

Data Index: 34259 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.2836. Min Act: -0.0000

Data Index: 107686 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.3585. Min Act: -0.0000

Data Index: 1135896 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.2342. Min Act: -0.0000

Data Index: 107624 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.2042. Min Act: -0.0000

Data Index: 507070 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.0468. Min Act: -0.0000

Data Index: 788582 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.0538. Min Act: -0.0000

Data Index: 594403 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 3.2887. Min Range: -3.2887

Max Act: 2.1840. Min Act: -0.0000

Data Index: 412259 (C4 (Web Text))

Max Activating Token Index: 439