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

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

Neuron 3495 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1631. Min Act: -0.0000

Data Index: 783055 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1375. Min Act: -0.0001

Data Index: 397371 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1530. Min Act: -0.0000

Data Index: 133948 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1440. Min Act: -0.0000

Data Index: 376650 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1187650 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1363. Min Act: -0.0000

Data Index: 385322 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1258397 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1459. Min Act: -0.0000

Data Index: 472639 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1367. Min Act: -0.0000

Data Index: 931601 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1353. Min Act: -0.0001

Data Index: 982183 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1332. Min Act: -0.0000

Data Index: 167093 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1277. Min Act: -0.0000

Data Index: 195260 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1191611 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1332. Min Act: -0.0000

Data Index: 920979 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1281. Min Act: -0.0000

Data Index: 361167 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1256. Min Act: -0.0000

Data Index: 962492 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1388. Min Act: -0.0000

Data Index: 798273 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1180. Min Act: -0.0000

Data Index: 630985 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1221894 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1052. Min Act: -0.0000

Data Index: 580546 (C4 (Web Text))

Max Activating Token Index: 707