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

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

Neuron 3036 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.6243. Min Act: -0.0001

Data Index: 355612 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4829. Min Act: -0.0001

Data Index: 972847 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.6419. Min Act: -0.0000

Data Index: 270922 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4374. Min Act: -0.0001

Data Index: 1215249 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5249. Min Act: -0.0001

Data Index: 5887 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4220. Min Act: -0.0000

Data Index: 961221 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3709. Min Act: -0.0000

Data Index: 313931 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4894. Min Act: -0.0000

Data Index: 849032 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4038. Min Act: -0.0001

Data Index: 785306 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4483. Min Act: -0.0000

Data Index: 675977 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4520. Min Act: -0.0001

Data Index: 254449 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4085. Min Act: -0.0000

Data Index: 1122618 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3494. Min Act: -0.0001

Data Index: 331225 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1102683 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4888. Min Act: -0.0000

Data Index: 231612 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4074. Min Act: -0.0000

Data Index: 663381 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5213. Min Act: -0.0000

Data Index: 75344 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3761. Min Act: -0.0000

Data Index: 113150 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3718. Min Act: -0.0001

Data Index: 626060 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3743. Min Act: -0.0001

Data Index: 55366 (C4 (Web Text))

Max Activating Token Index: 744