Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 127 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.7516. Min Act: -0.0001

Data Index: 278470 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.7168. Min Act: -0.0001

Data Index: 1342377 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.7398. Min Act: -0.0001

Data Index: 247586 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6994. Min Act: -0.0001

Data Index: 720753 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6892. Min Act: -0.0001

Data Index: 446260 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6672. Min Act: -0.0001

Data Index: 1066595 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6601. Min Act: -0.0001

Data Index: 1284757 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4959. Min Act: -0.0001

Data Index: 122473 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6705. Min Act: -0.0001

Data Index: 1256921 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6031. Min Act: -0.0001

Data Index: 95241 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6663. Min Act: -0.0001

Data Index: 940840 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6466. Min Act: -0.0001

Data Index: 759398 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6151. Min Act: -0.0002

Data Index: 174488 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6563. Min Act: -0.0001

Data Index: 784581 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6319. Min Act: -0.0001

Data Index: 259564 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6080. Min Act: -0.0002

Data Index: 364680 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6034. Min Act: -0.0001

Data Index: 1119987 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6430. Min Act: -0.0001

Data Index: 316530 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6001. Min Act: -0.0001

Data Index: 236419 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6445. Min Act: -0.0002

Data Index: 346066 (C4 (Web Text))

Max Activating Token Index: 826