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

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

Neuron 4967 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4490. Min Range: -2.4490

Max Act: 2.4490. Min Act: -0.0000

Data Index: 1192574 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 2.4490. Min Range: -2.4490

Max Act: 2.2061. Min Act: -0.0000

Data Index: 854306 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 2.4490. Min Range: -2.4490

Max Act: 2.0120. Min Act: -0.0000

Data Index: 1037335 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.9751. Min Act: -0.0000

Data Index: 1285567 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 2.4490. Min Range: -2.4490

Max Act: 2.1407. Min Act: -0.0000

Data Index: 412849 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.7887. Min Act: -0.0000

Data Index: 637169 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.6125. Min Act: -0.0000

Data Index: 680516 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.4711. Min Act: -0.0000

Data Index: 1203736 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.5755. Min Act: -0.0000

Data Index: 438813 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.4101. Min Act: -0.0000

Data Index: 908120 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.5284. Min Act: -0.0000

Data Index: 1144457 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.4821. Min Act: -0.0000

Data Index: 387497 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.5092. Min Act: -0.0000

Data Index: 105449 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.4243. Min Act: -0.0000

Data Index: 1209464 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.3921. Min Act: -0.0000

Data Index: 1041052 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1081399 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.2747. Min Act: -0.0000

Data Index: 918449 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.3880. Min Act: -0.0000

Data Index: 331303 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.4314. Min Act: -0.0000

Data Index: 709500 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 2.4490. Min Range: -2.4490

Max Act: 1.3596. Min Act: -0.0000

Data Index: 222101 (C4 (Web Text))

Max Activating Token Index: 924