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

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

Neuron 2499 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1397. Min Act: -0.0002

Data Index: 865885 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1266. Min Act: -0.0002

Data Index: 206921 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1408. Min Act: -0.0002

Data Index: 508118 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1333. Min Act: -0.0002

Data Index: 355943 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1393. Min Act: -0.0002

Data Index: 353413 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1349. Min Act: -0.0001

Data Index: 643105 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1531. Min Act: -0.0002

Data Index: 1020494 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1301. Min Act: -0.0001

Data Index: 854019 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1176724 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1066. Min Act: -0.0001

Data Index: 859923 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1183849 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1083944 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1201. Min Act: -0.0002

Data Index: 1359507 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1146086 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1296805 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1206. Min Act: -0.0002

Data Index: 140453 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1146944 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1009176 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1371. Min Act: -0.0002

Data Index: 459983 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1142. Min Act: -0.0002

Data Index: 394683 (C4 (Web Text))

Max Activating Token Index: 417