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

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

Neuron 3141 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: 1.8246. Min Range: -1.8246

Max Act: 1.6374. Min Act: -0.0001

Data Index: 1313172 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.5321. Min Act: -0.0001

Data Index: 568144 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.8246. Min Act: -0.0001

Data Index: 408900 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.3718. Min Act: -0.0001

Data Index: 590181 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.2919. Min Act: -0.0001

Data Index: 383999 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.4240. Min Act: -0.0001

Data Index: 574496 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.2552. Min Act: -0.0001

Data Index: 1149935 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.1589. Min Act: -0.0001

Data Index: 1057923 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.0739. Min Act: -0.0001

Data Index: 1591687 (Python Code)

Max Activating Token Index: 319

Text #9

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.1624. Min Act: -0.0001

Data Index: 415164 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.0915. Min Act: -0.0001

Data Index: 280573 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.0914. Min Act: -0.0001

Data Index: 552270 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 1.8246. Min Range: -1.8246

Max Act: 0.9193. Min Act: -0.0001

Data Index: 518512 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.1190. Min Act: -0.0001

Data Index: 785220 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.0493. Min Act: -0.0001

Data Index: 599227 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 1.8246. Min Range: -1.8246

Max Act: 1.0211. Min Act: -0.0001

Data Index: 951868 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 1.8246. Min Range: -1.8246

Max Act: 0.9478. Min Act: -0.0001

Data Index: 915069 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.8246. Min Range: -1.8246

Max Act: 0.9134. Min Act: -0.0001

Data Index: 687868 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 1.8246. Min Range: -1.8246

Max Act: 0.9125. Min Act: -0.0001

Data Index: 548429 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 1.8246. Min Range: -1.8246

Max Act: 0.9167. Min Act: -0.0001

Data Index: 589846 (C4 (Web Text))

Max Activating Token Index: 867