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

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

Neuron 2108 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0004

Data Index: 1078664 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0332. Min Act: -0.0004

Data Index: 1353786 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0328. Min Act: -0.0004

Data Index: 214921 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0326. Min Act: -0.0004

Data Index: 1029567 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0302. Min Act: -0.0004

Data Index: 1092442 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0324. Min Act: -0.0004

Data Index: 1149297 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0314. Min Act: -0.0004

Data Index: 506794 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0317. Min Act: -0.0004

Data Index: 192956 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0293. Min Act: -0.0004

Data Index: 1272592 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0311. Min Act: -0.0004

Data Index: 612810 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0319. Min Act: -0.0004

Data Index: 659318 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0281. Min Act: -0.0004

Data Index: 701699 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0305. Min Act: -0.0004

Data Index: 496119 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0311. Min Act: -0.0004

Data Index: 139300 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0320. Min Act: -0.0004

Data Index: 74033 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0308. Min Act: -0.0004

Data Index: 862723 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0308. Min Act: -0.0004

Data Index: 403287 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0307. Min Act: -0.0004

Data Index: 1351443 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0301. Min Act: -0.0004

Data Index: 932397 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0300. Min Act: -0.0004

Data Index: 553745 (C4 (Web Text))

Max Activating Token Index: 716