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

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

Neuron 341 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: 0.1495. Min Range: -0.1495

Max Act: 0.1495. Min Act: -0.0001

Data Index: 251389 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1159030 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1361. Min Act: -0.0001

Data Index: 523765 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1385. Min Act: -0.0001

Data Index: 784133 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1320206 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1267. Min Act: -0.0001

Data Index: 614287 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1266589 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1319. Min Act: -0.0001

Data Index: 406085 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1108. Min Act: -0.0001

Data Index: 33734 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1318302 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1103. Min Act: -0.0001

Data Index: 870921 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1103. Min Act: -0.0001

Data Index: 477231 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1123. Min Act: -0.0001

Data Index: 95378 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1128. Min Act: -0.0001

Data Index: 203727 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1007072 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1121618 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1032. Min Act: -0.0001

Data Index: 922819 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1109. Min Act: -0.0001

Data Index: 559553 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1094. Min Act: -0.0001

Data Index: 872205 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1108. Min Act: -0.0001

Data Index: 371439 (C4 (Web Text))

Max Activating Token Index: 488