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

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

Neuron 2891 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.3353. Min Act: -0.0000

Data Index: 770031 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.3157. Min Act: -0.0001

Data Index: 1254736 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.0490. Min Act: -0.0000

Data Index: 467330 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1145589 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.0203. Min Act: -0.0000

Data Index: 818742 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9591. Min Act: -0.0000

Data Index: 647005 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1002820 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1331384 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1326440 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1082960 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.8617. Min Act: -0.0000

Data Index: 853557 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.8834. Min Act: -0.0000

Data Index: 555549 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9026. Min Act: -0.0000

Data Index: 542148 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.9051. Min Act: -0.0000

Data Index: 963095 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.8504. Min Act: -0.0000

Data Index: 104932 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 1.3353. Min Range: -1.3353

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1348058 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.8567. Min Act: -0.0000

Data Index: 491180 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.8776. Min Act: -0.0000

Data Index: 47006 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.8465. Min Act: -0.0000

Data Index: 265887 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 1.3353. Min Range: -1.3353

Max Act: 0.8870. Min Act: -0.0000

Data Index: 913248 (C4 (Web Text))

Max Activating Token Index: 38