Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5248 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.4215. Min Act: -0.0000

Data Index: 688274 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1157121 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.4043. Min Act: -0.0000

Data Index: 406569 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3756. Min Act: -0.0000

Data Index: 922828 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3665. Min Act: -0.0000

Data Index: 59703 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3423. Min Act: -0.0000

Data Index: 966502 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3327. Min Act: -0.0000

Data Index: 237214 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3420. Min Act: 0.0001

Data Index: 600257 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3472. Min Act: -0.0000

Data Index: 185908 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3029. Min Act: 0.0000

Data Index: 1091306 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3282. Min Act: -0.0000

Data Index: 634464 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3295. Min Act: -0.0000

Data Index: 601433 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3280. Min Act: -0.0000

Data Index: 404299 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3127. Min Act: -0.0000

Data Index: 437426 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3126. Min Act: -0.0000

Data Index: 307279 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3116. Min Act: -0.0000

Data Index: 956374 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3086. Min Act: 0.0000

Data Index: 369759 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1311613 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2998. Min Act: -0.0000

Data Index: 703222 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.2994. Min Act: -0.0000

Data Index: 806543 (C4 (Web Text))

Max Activating Token Index: 371