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

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

Neuron 204 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8452. Min Range: -2.8452

Max Act: 2.8452. Min Act: -0.0000

Data Index: 145208 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 2.8452. Min Range: -2.8452

Max Act: 2.6536. Min Act: -0.0000

Data Index: 930564 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.6011. Min Act: -0.0000

Data Index: 795450 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.5418. Min Act: -0.0000

Data Index: 845063 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.6074. Min Act: -0.0000

Data Index: 18752 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.3708. Min Act: -0.0000

Data Index: 754192 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.4396. Min Act: -0.0000

Data Index: 801283 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.5249. Min Act: -0.0000

Data Index: 312281 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.4060. Min Act: -0.0000

Data Index: 209096 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.1962. Min Act: -0.0000

Data Index: 164504 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.2587. Min Act: -0.0000

Data Index: 767523 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.3201. Min Act: -0.0000

Data Index: 235633 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.2864. Min Act: -0.0000

Data Index: 1248243 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.1142. Min Act: -0.0000

Data Index: 813617 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.1335. Min Act: -0.0000

Data Index: 504499 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.2527. Min Act: -0.0000

Data Index: 1239614 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.1890. Min Act: -0.0000

Data Index: 113720 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.0464. Min Act: -0.0000

Data Index: 4481 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.0930. Min Act: -0.0000

Data Index: 715082 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 2.8452. Min Range: -2.8452

Max Act: 1.1325. Min Act: -0.0000

Data Index: 465600 (C4 (Web Text))

Max Activating Token Index: 27