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

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

Neuron 1264 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1050510 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5048. Min Act: -0.0000

Data Index: 746926 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1099311 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4955. Min Act: -0.0000

Data Index: 415565 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1037363 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4838. Min Act: -0.0000

Data Index: 922088 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1033615 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4806. Min Act: -0.0000

Data Index: 50564 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4738. Min Act: -0.0000

Data Index: 334613 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1090057 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4487. Min Act: -0.0000

Data Index: 75284 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4449. Min Act: -0.0000

Data Index: 960911 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1198315 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1057174 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1108122 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4163. Min Act: -0.0000

Data Index: 2450 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.3992. Min Act: -0.0000

Data Index: 905411 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4445. Min Act: -0.0000

Data Index: 95776 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4209. Min Act: -0.0000

Data Index: 984744 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4247. Min Act: -0.0000

Data Index: 673088 (C4 (Web Text))

Max Activating Token Index: 536