Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 710 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.9916. Min Act: -0.0003

Data Index: 295318 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.3408. Min Act: -0.0003

Data Index: 1158227 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.1281. Min Act: -0.0003

Data Index: 668197 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.1215. Min Act: -0.0003

Data Index: 1202123 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.0108. Min Act: -0.0003

Data Index: 1525674 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.0060. Min Act: -0.0003

Data Index: 914284 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.9277. Min Act: -0.0003

Data Index: 269258 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.9534. Min Act: -0.0003

Data Index: 339028 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.9490. Min Act: -0.0003

Data Index: 394531 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.9486. Min Act: -0.0003

Data Index: 787269 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.9690. Min Act: -0.0004

Data Index: 124211 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.9481. Min Act: -0.0003

Data Index: 79929 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.8323. Min Act: -0.0003

Data Index: 1489 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.9420. Min Act: -0.0003

Data Index: 1610859 (Python Code)

Max Activating Token Index: 286

Text #14

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.9708. Min Act: -0.0003

Data Index: 1145720 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.9216. Min Act: -0.0003

Data Index: 972741 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.9116. Min Act: -0.0003

Data Index: 780427 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.8843. Min Act: -0.0003

Data Index: 995362 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.8291. Min Act: -0.0003

Data Index: 447948 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 1.9916. Min Range: -1.9916

Max Act: 0.8542. Min Act: -0.0003

Data Index: 138734 (C4 (Web Text))

Max Activating Token Index: 583