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

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

Neuron 2752 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0003

Data Index: 554188 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1317620 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0358. Min Act: -0.0003

Data Index: 556016 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0332. Min Act: -0.0003

Data Index: 72943 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0328. Min Act: -0.0003

Data Index: 969274 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0333. Min Act: -0.0003

Data Index: 651643 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0308. Min Act: -0.0003

Data Index: 207320 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1049351 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0298. Min Act: -0.0003

Data Index: 272145 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1094272 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0329. Min Act: -0.0003

Data Index: 701477 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1115866 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1306254 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0288. Min Act: -0.0003

Data Index: 755269 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0303. Min Act: -0.0003

Data Index: 257961 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0313. Min Act: -0.0003

Data Index: 215369 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0289. Min Act: -0.0003

Data Index: 163136 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0303. Min Act: -0.0003

Data Index: 669431 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1092516 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0308. Min Act: -0.0003

Data Index: 199339 (C4 (Web Text))

Max Activating Token Index: 214