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

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

Neuron 3045 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: 1.0035. Min Range: -1.0035

Max Act: 0.9924. Min Act: -0.0001

Data Index: 566332 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.9650. Min Act: -0.0001

Data Index: 89298 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.0035. Min Range: -1.0035

Max Act: 1.0035. Min Act: -0.0001

Data Index: 1050480 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.8377. Min Act: -0.0001

Data Index: 301519 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.8450. Min Act: -0.0001

Data Index: 1055703 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7708. Min Act: -0.0001

Data Index: 283380 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7869. Min Act: -0.0001

Data Index: 64684 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7801. Min Act: -0.0001

Data Index: 345864 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7500. Min Act: -0.0001

Data Index: 993156 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7429. Min Act: -0.0001

Data Index: 160142 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7678. Min Act: -0.0001

Data Index: 170778 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7294. Min Act: -0.0001

Data Index: 799444 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7572. Min Act: -0.0001

Data Index: 292947 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7452. Min Act: -0.0001

Data Index: 974425 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7223. Min Act: -0.0001

Data Index: 1100241 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7624. Min Act: -0.0001

Data Index: 942649 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.6683. Min Act: -0.0001

Data Index: 492150 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7351. Min Act: -0.0001

Data Index: 227000 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7217. Min Act: -0.0001

Data Index: 1039713 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7457. Min Act: -0.0001

Data Index: 229786 (C4 (Web Text))

Max Activating Token Index: 526