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

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

Neuron 2500 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: 2.2432. Min Range: -2.2432

Max Act: 1.8587. Min Act: -0.0000

Data Index: 169026 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 2.2432. Min Range: -2.2432

Max Act: 2.2432. Min Act: -0.0000

Data Index: 456321 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.8473. Min Act: -0.0000

Data Index: 916225 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.8557. Min Act: -0.0000

Data Index: 350418 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 2.2432. Min Range: -2.2432

Max Act: 2.0332. Min Act: -0.0000

Data Index: 1303765 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.8267. Min Act: -0.0001

Data Index: 219949 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.7994. Min Act: -0.0000

Data Index: 200718 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.5953. Min Act: -0.0000

Data Index: 1262329 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.4961. Min Act: -0.0001

Data Index: 338871 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.5348. Min Act: -0.0000

Data Index: 273671 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.5216. Min Act: -0.0001

Data Index: 1214949 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.5157. Min Act: -0.0000

Data Index: 1039206 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.4050. Min Act: -0.0001

Data Index: 394081 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.4359. Min Act: -0.0000

Data Index: 1151698 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.2389. Min Act: -0.0001

Data Index: 200169 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.4967. Min Act: -0.0000

Data Index: 1069874 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.4808. Min Act: -0.0000

Data Index: 132940 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.4692. Min Act: -0.0000

Data Index: 154348 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.4848. Min Act: -0.0000

Data Index: 360721 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 2.2432. Min Range: -2.2432

Max Act: 1.3668. Min Act: -0.0000

Data Index: 369709 (C4 (Web Text))

Max Activating Token Index: 901