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

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

Neuron 305 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: 0.0348. Min Range: -0.0348

Max Act: 0.0348. Min Act: -0.0004

Data Index: 1172183 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0344. Min Act: -0.0004

Data Index: 534769 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0279. Min Act: -0.0004

Data Index: 465017 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0310. Min Act: -0.0004

Data Index: 1221417 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0336. Min Act: -0.0004

Data Index: 1055430 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0301. Min Act: -0.0004

Data Index: 993340 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0298. Min Act: -0.0004

Data Index: 1053668 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0286. Min Act: -0.0004

Data Index: 469745 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0265. Min Act: -0.0004

Data Index: 996685 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0273. Min Act: -0.0004

Data Index: 1168510 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0288. Min Act: -0.0004

Data Index: 478634 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0297. Min Act: -0.0004

Data Index: 1165821 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0285. Min Act: -0.0004

Data Index: 749953 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0250. Min Act: -0.0004

Data Index: 74659 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0291. Min Act: -0.0004

Data Index: 198671 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0271. Min Act: -0.0004

Data Index: 343855 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0277. Min Act: -0.0004

Data Index: 831970 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0287. Min Act: -0.0004

Data Index: 704851 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0282. Min Act: -0.0004

Data Index: 794675 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0258. Min Act: -0.0004

Data Index: 123935 (C4 (Web Text))

Max Activating Token Index: 393