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

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

Neuron 4675 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: 1.5958. Min Range: -1.5958

Max Act: 1.5383. Min Act: -0.0000

Data Index: 129162 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.5958. Min Act: -0.0000

Data Index: 706729 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.4829. Min Act: -0.0000

Data Index: 62648 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.5539. Min Act: -0.0000

Data Index: 497472 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.4440. Min Act: -0.0000

Data Index: 1109855 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.3218. Min Act: -0.0000

Data Index: 416805 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.4647. Min Act: -0.0000

Data Index: 1050938 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1262159 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.4562. Min Act: -0.0000

Data Index: 1001391 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.3708. Min Act: -0.0000

Data Index: 560181 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.3708. Min Act: -0.0000

Data Index: 663244 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.3812. Min Act: -0.0000

Data Index: 248608 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.3047. Min Act: -0.0000

Data Index: 796820 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.3015. Min Act: -0.0000

Data Index: 686913 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.2449. Min Act: -0.0000

Data Index: 191381 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1357385 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.3526. Min Act: -0.0000

Data Index: 348000 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.2386. Min Act: -0.0000

Data Index: 807018 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.3353. Min Act: -0.0000

Data Index: 761354 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 1.5958. Min Range: -1.5958

Max Act: 1.2794. Min Act: -0.0000

Data Index: 1227538 (C4 (Web Text))

Max Activating Token Index: 489