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

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

Neuron 1527 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3345. Min Range: -3.3345

Max Act: 3.3345. Min Act: -0.0000

Data Index: 1566612 (Python Code)

Max Activating Token Index: 495

Text #1

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.9619. Min Act: -0.0000

Data Index: 302459 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 3.3345. Min Range: -3.3345

Max Act: 3.1005. Min Act: -0.0001

Data Index: 214167 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.7731. Min Act: -0.0000

Data Index: 678406 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.5500. Min Act: -0.0001

Data Index: 1587454 (Python Code)

Max Activating Token Index: 602

Text #5

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.5102. Min Act: -0.0000

Data Index: 35701 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.2622. Min Act: -0.0000

Data Index: 1203240 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.5621. Min Act: -0.0000

Data Index: 357250 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.4263. Min Act: -0.0000

Data Index: 991781 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.2725. Min Act: -0.0000

Data Index: 1303142 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.2471. Min Act: -0.0000

Data Index: 595479 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.2113. Min Act: -0.0000

Data Index: 1054152 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.2779. Min Act: -0.0000

Data Index: 305898 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.3067. Min Act: -0.0000

Data Index: 17006 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.3081. Min Act: -0.0000

Data Index: 1559337 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.2527. Min Act: -0.0000

Data Index: 1461256 (Python Code)

Max Activating Token Index: 268

Text #16

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.1753. Min Act: -0.0000

Data Index: 1198803 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.2307. Min Act: -0.0001

Data Index: 1015003 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.2394. Min Act: -0.0000

Data Index: 776362 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 3.3345. Min Range: -3.3345

Max Act: 2.2073. Min Act: -0.0000

Data Index: 139873 (C4 (Web Text))

Max Activating Token Index: 695