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

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

Neuron 4311 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: 0.1883. Min Range: -0.1883

Max Act: 0.1883. Min Act: -0.0001

Data Index: 222912 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1799. Min Act: -0.0001

Data Index: 252250 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1757. Min Act: -0.0001

Data Index: 538503 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1854. Min Act: -0.0001

Data Index: 97974 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1815. Min Act: -0.0001

Data Index: 97409 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1700. Min Act: -0.0001

Data Index: 794303 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1556. Min Act: -0.0001

Data Index: 950464 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1747. Min Act: -0.0001

Data Index: 398611 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1548. Min Act: -0.0001

Data Index: 1254561 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1325. Min Act: -0.0001

Data Index: 447232 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1357. Min Act: -0.0001

Data Index: 918199 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1318. Min Act: -0.0001

Data Index: 27897 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1081877 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1294. Min Act: -0.0001

Data Index: 597745 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1305. Min Act: -0.0001

Data Index: 950266 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1282. Min Act: -0.0001

Data Index: 179118 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1133. Min Act: -0.0001

Data Index: 882106 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1304. Min Act: -0.0001

Data Index: 802345 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1176. Min Act: -0.0001

Data Index: 53445 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1599360 (Python Code)

Max Activating Token Index: 641