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

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

Neuron 5268 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.9796. Min Act: -0.0000

Data Index: 118347 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.7839. Min Act: -0.0000

Data Index: 350025 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.7271. Min Act: -0.0000

Data Index: 718583 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.3823. Min Act: -0.0000

Data Index: 1063784 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.3118. Min Act: -0.0000

Data Index: 1300051 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.2955. Min Act: -0.0000

Data Index: 804426 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.2864. Min Act: -0.0000

Data Index: 1377471 (Python Code)

Max Activating Token Index: 483

Text #7

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.2891. Min Act: -0.0000

Data Index: 1048269 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.2546. Min Act: -0.0000

Data Index: 1103511 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.2112. Min Act: -0.0000

Data Index: 635889 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.2129. Min Act: -0.0000

Data Index: 274329 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.1862. Min Act: -0.0000

Data Index: 470895 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.1777. Min Act: -0.0000

Data Index: 1369166 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.1506. Min Act: -0.0000

Data Index: 970847 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.0043. Min Act: -0.0000

Data Index: 811677 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.1413. Min Act: -0.0000

Data Index: 314577 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.1262. Min Act: -0.0000

Data Index: 141165 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 3.9796. Min Range: -3.9796

Max Act: 2.9767. Min Act: -0.0000

Data Index: 661681 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.1184. Min Act: -0.0000

Data Index: 1023229 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 3.9796. Min Range: -3.9796

Max Act: 3.0895. Min Act: -0.0000

Data Index: 1485787 (Python Code)

Max Activating Token Index: 87