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

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

Neuron 1940 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: 0.0374. Min Range: -0.0374

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1108598 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0374. Min Act: -0.0003

Data Index: 733720 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0354. Min Act: -0.0003

Data Index: 288432 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0354. Min Act: -0.0003

Data Index: 740201 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1265907 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0320. Min Act: -0.0003

Data Index: 969931 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0324. Min Act: -0.0003

Data Index: 255539 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1223141 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0325. Min Act: -0.0003

Data Index: 510558 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0290. Min Act: -0.0003

Data Index: 429989 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0309. Min Act: -0.0003

Data Index: 469248 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0280. Min Act: -0.0003

Data Index: 776164 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0341. Min Act: -0.0003

Data Index: 162628 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0313. Min Act: -0.0003

Data Index: 244504 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0296. Min Act: -0.0003

Data Index: 832592 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1182828 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1013942 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0284. Min Act: -0.0003

Data Index: 159907 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0281. Min Act: -0.0003

Data Index: 414629 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0286. Min Act: -0.0003

Data Index: 597633 (C4 (Web Text))

Max Activating Token Index: 891