Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1283 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8713. Min Act: -0.0001

Data Index: 332337 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8651. Min Act: -0.0001

Data Index: 226991 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8775. Min Act: -0.0001

Data Index: 487741 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8674. Min Act: -0.0001

Data Index: 827324 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8632. Min Act: -0.0001

Data Index: 503640 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8903. Min Act: -0.0001

Data Index: 684255 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8381. Min Act: -0.0001

Data Index: 897259 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8208. Min Act: -0.0001

Data Index: 814035 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8163. Min Act: -0.0001

Data Index: 913559 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8405. Min Act: -0.0001

Data Index: 588317 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8420. Min Act: -0.0001

Data Index: 471371 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8341. Min Act: -0.0001

Data Index: 1109867 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8283. Min Act: -0.0001

Data Index: 719781 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8265. Min Act: -0.0001

Data Index: 69571 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7716. Min Act: -0.0001

Data Index: 130870 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8501. Min Act: -0.0001

Data Index: 981045 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8180. Min Act: -0.0001

Data Index: 1003305 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7972. Min Act: -0.0001

Data Index: 819768 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7378. Min Act: -0.0001

Data Index: 104625 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8107. Min Act: -0.0001

Data Index: 1308674 (C4 (Web Text))

Max Activating Token Index: 665