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

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

Neuron 3263 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1841. Min Act: -0.0000

Data Index: 482400 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1265145 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1331. Min Act: -0.0001

Data Index: 183829 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1705. Min Act: -0.0001

Data Index: 429290 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1451. Min Act: -0.0000

Data Index: 13534 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1487. Min Act: -0.0000

Data Index: 421336 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1424. Min Act: -0.0001

Data Index: 176971 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1137. Min Act: -0.0000

Data Index: 12887 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1367. Min Act: -0.0000

Data Index: 150876 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1429. Min Act: -0.0001

Data Index: 3137 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1579. Min Act: -0.0000

Data Index: 860169 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1462. Min Act: -0.0001

Data Index: 67993 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1469. Min Act: -0.0001

Data Index: 31558 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1104197 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1275. Min Act: -0.0000

Data Index: 957916 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1167273 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1248. Min Act: -0.0001

Data Index: 4096 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1361. Min Act: -0.0000

Data Index: 480031 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1227. Min Act: -0.0000

Data Index: 581068 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1272552 (C4 (Web Text))

Max Activating Token Index: 728