Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3505 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.5536. Min Act: -0.0001

Data Index: 584957 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.6217. Min Act: -0.0001

Data Index: 696051 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.5302. Min Act: -0.0001

Data Index: 1352987 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.4531. Min Act: -0.0001

Data Index: 1321264 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.2773. Min Act: -0.0001

Data Index: 490385 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.4686. Min Act: -0.0001

Data Index: 150776 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.4035. Min Act: -0.0001

Data Index: 1028999 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.2891. Min Act: -0.0001

Data Index: 213476 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.3210. Min Act: -0.0001

Data Index: 813871 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.2307. Min Act: -0.0001

Data Index: 1013245 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.2533. Min Act: -0.0001

Data Index: 667442 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.2083. Min Act: -0.0001

Data Index: 1171448 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.2407. Min Act: -0.0001

Data Index: 1064183 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.2227. Min Act: -0.0001

Data Index: 30222 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.2026. Min Act: -0.0001

Data Index: 150967 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.1271. Min Act: -0.0001

Data Index: 1228724 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.1612. Min Act: -0.0001

Data Index: 201662 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.1243. Min Act: -0.0001

Data Index: 302253 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.2031. Min Act: -0.0001

Data Index: 1161046 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 1.6217. Min Range: -1.6217

Max Act: 1.1415. Min Act: -0.0001

Data Index: 183497 (C4 (Web Text))

Max Activating Token Index: 77