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

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

Neuron 5268 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: 1.8705. Min Range: -1.8705

Max Act: 1.8705. Min Act: -0.0001

Data Index: 697219 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.7860. Min Act: -0.0001

Data Index: 618715 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.5003. Min Act: -0.0001

Data Index: 577149 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.3383. Min Act: -0.0001

Data Index: 179784 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.3148. Min Act: -0.0001

Data Index: 240056 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.2313. Min Act: -0.0001

Data Index: 764948 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0815. Min Act: -0.0001

Data Index: 12006 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.1149. Min Act: -0.0001

Data Index: 672982 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0692. Min Act: -0.0001

Data Index: 1239580 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0511. Min Act: -0.0001

Data Index: 1308573 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0505. Min Act: -0.0001

Data Index: 790752 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0927. Min Act: -0.0001

Data Index: 27343 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0894. Min Act: -0.0001

Data Index: 1197090 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.8705. Min Range: -1.8705

Max Act: 0.9986. Min Act: -0.0001

Data Index: 1207265 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0616. Min Act: -0.0001

Data Index: 559064 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 1.8705. Min Range: -1.8705

Max Act: 0.9701. Min Act: -0.0001

Data Index: 987180 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0850. Min Act: -0.0001

Data Index: 160397 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 1.8705. Min Range: -1.8705

Max Act: 0.9533. Min Act: -0.0001

Data Index: 973873 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0634. Min Act: -0.0001

Data Index: 1306109 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0775. Min Act: -0.0001

Data Index: 1094407 (C4 (Web Text))

Max Activating Token Index: 655