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

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

Neuron 1606 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: 1.5451. Min Range: -1.5451

Max Act: 1.5451. Min Act: -0.0001

Data Index: 608069 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.3830. Min Act: -0.0001

Data Index: 36009 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.3255. Min Act: -0.0001

Data Index: 1345283 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.1945. Min Act: -0.0001

Data Index: 953473 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.0848. Min Act: -0.0001

Data Index: 148301 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.1109. Min Act: -0.0001

Data Index: 610358 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.1016. Min Act: -0.0001

Data Index: 873914 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.1125. Min Act: -0.0001

Data Index: 1278366 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.0767. Min Act: -0.0001

Data Index: 220271 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.0436. Min Act: -0.0001

Data Index: 941034 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.1070. Min Act: -0.0001

Data Index: 813503 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.0726. Min Act: -0.0001

Data Index: 493320 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.0505. Min Act: -0.0001

Data Index: 690565 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.1243. Min Act: -0.0001

Data Index: 483365 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.0614. Min Act: -0.0001

Data Index: 514632 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.0283. Min Act: -0.0001

Data Index: 223239 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.0348. Min Act: -0.0001

Data Index: 290169 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.0367. Min Act: -0.0001

Data Index: 315633 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.0272. Min Act: -0.0001

Data Index: 258885 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.5451. Min Range: -1.5451

Max Act: 1.0266. Min Act: -0.0001

Data Index: 1133123 (C4 (Web Text))

Max Activating Token Index: 528