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

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

Neuron 706 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: 0.0463. Min Range: -0.0463

Max Act: 0.0463. Min Act: -0.0004

Data Index: 990828 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0425. Min Act: -0.0004

Data Index: 649267 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0367. Min Act: -0.0004

Data Index: 165865 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0345. Min Act: -0.0004

Data Index: 356873 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0336. Min Act: -0.0004

Data Index: 604707 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0349. Min Act: -0.0004

Data Index: 27306 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0335. Min Act: -0.0004

Data Index: 542368 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0325. Min Act: -0.0004

Data Index: 290845 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0325. Min Act: -0.0004

Data Index: 374918 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0310. Min Act: -0.0004

Data Index: 168816 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0327. Min Act: -0.0004

Data Index: 918848 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0326. Min Act: -0.0004

Data Index: 1217515 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1326102 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0293. Min Act: -0.0004

Data Index: 738532 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0274. Min Act: -0.0004

Data Index: 1191960 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0288. Min Act: -0.0004

Data Index: 5337 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0271. Min Act: -0.0004

Data Index: 65506 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0300. Min Act: -0.0004

Data Index: 548034 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0316. Min Act: -0.0004

Data Index: 1296054 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0308. Min Act: -0.0004

Data Index: 705624 (C4 (Web Text))

Max Activating Token Index: 1012