Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3316 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.9382. Min Act: -0.0001

Data Index: 958596 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8862. Min Act: -0.0001

Data Index: 1312797 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7536. Min Act: -0.0001

Data Index: 194165 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8457. Min Act: -0.0000

Data Index: 977644 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8278. Min Act: -0.0001

Data Index: 278773 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7960. Min Act: -0.0001

Data Index: 1025403 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7728. Min Act: -0.0000

Data Index: 478564 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7849. Min Act: -0.0001

Data Index: 330917 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7493. Min Act: -0.0001

Data Index: 746571 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7133. Min Act: -0.0001

Data Index: 347623 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7256. Min Act: -0.0001

Data Index: 558267 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7287. Min Act: -0.0001

Data Index: 881406 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6952. Min Act: -0.0001

Data Index: 917394 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7300. Min Act: -0.0001

Data Index: 288617 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6833. Min Act: -0.0001

Data Index: 98926 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6849. Min Act: -0.0001

Data Index: 973304 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6975. Min Act: -0.0000

Data Index: 526739 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6210. Min Act: -0.0001

Data Index: 368226 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6888. Min Act: -0.0001

Data Index: 996497 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7021. Min Act: -0.0000

Data Index: 648517 (C4 (Web Text))

Max Activating Token Index: 201