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

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

Neuron 4300 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9044. Min Range: -5.9044

Max Act: 5.9044. Min Act: -0.0001

Data Index: 405422 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 5.9044. Min Range: -5.9044

Max Act: 5.3051. Min Act: -0.0001

Data Index: 789996 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.7574. Min Act: -0.0001

Data Index: 1088361 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 5.9044. Min Range: -5.9044

Max Act: 5.3778. Min Act: -0.0001

Data Index: 187743 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.3527. Min Act: -0.0001

Data Index: 137299 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.6196. Min Act: -0.0001

Data Index: 1328528 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.7906. Min Act: -0.0001

Data Index: 1252684 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.3942. Min Act: -0.0001

Data Index: 563960 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.5432. Min Act: -0.0001

Data Index: 1322025 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.2734. Min Act: -0.0001

Data Index: 251219 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.4665. Min Act: -0.0001

Data Index: 305069 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.2614. Min Act: -0.0001

Data Index: 213198 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 5.9044. Min Range: -5.9044

Max Act: 3.9157. Min Act: -0.0001

Data Index: 863037 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.1624. Min Act: -0.0001

Data Index: 386358 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.5960. Min Act: -0.0001

Data Index: 319643 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 5.9044. Min Range: -5.9044

Max Act: 3.5827. Min Act: -0.0001

Data Index: 74683 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.0900. Min Act: -0.0001

Data Index: 1283912 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.0443. Min Act: -0.0001

Data Index: 1349464 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.3995. Min Act: -0.0001

Data Index: 163784 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 5.9044. Min Range: -5.9044

Max Act: 4.0686. Min Act: -0.0001

Data Index: 361392 (C4 (Web Text))

Max Activating Token Index: 462