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

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

Neuron 33 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3432. Min Act: -0.0002

Data Index: 64419 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4859. Min Act: -0.0001

Data Index: 442682 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3495. Min Act: -0.0001

Data Index: 1237337 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.0418. Min Act: -0.0001

Data Index: 183732 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.9721. Min Act: -0.0001

Data Index: 1177187 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.0259. Min Act: -0.0002

Data Index: 715895 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.1476. Min Act: -0.0002

Data Index: 1322458 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.9842. Min Act: -0.0002

Data Index: 199676 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.9764. Min Act: -0.0002

Data Index: 938329 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.7382. Min Act: -0.0002

Data Index: 65279 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.8678. Min Act: -0.0001

Data Index: 1269203 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.1125. Min Act: -0.0001

Data Index: 1120755 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.8991. Min Act: -0.0001

Data Index: 918289 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.8911. Min Act: -0.0002

Data Index: 968351 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.6319. Min Act: -0.0001

Data Index: 135922 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.8648. Min Act: -0.0001

Data Index: 877519 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.7177. Min Act: -0.0001

Data Index: 793568 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.5847. Min Act: -0.0001

Data Index: 465141 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.3822. Min Act: -0.0002

Data Index: 1335964 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 3.4859. Min Range: -3.4859

Max Act: 2.7171. Min Act: -0.0001

Data Index: 688770 (C4 (Web Text))

Max Activating Token Index: 154