Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1604 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5846. Min Act: -0.0001

Data Index: 791771 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5496. Min Act: -0.0000

Data Index: 231388 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5283. Min Act: -0.0001

Data Index: 333455 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5520. Min Act: -0.0001

Data Index: 502125 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5253. Min Act: -0.0001

Data Index: 662087 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5036. Min Act: -0.0001

Data Index: 1219705 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4834. Min Act: -0.0001

Data Index: 1233814 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4791. Min Act: -0.0001

Data Index: 887126 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4896. Min Act: -0.0001

Data Index: 1182330 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4702. Min Act: -0.0001

Data Index: 1044301 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4817. Min Act: -0.0001

Data Index: 1290022 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4448. Min Act: -0.0001

Data Index: 703512 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4568. Min Act: -0.0001

Data Index: 37027 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4543. Min Act: -0.0001

Data Index: 252230 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4637. Min Act: -0.0001

Data Index: 30973 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4442. Min Act: -0.0000

Data Index: 601363 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4571. Min Act: -0.0001

Data Index: 167960 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4366. Min Act: -0.0001

Data Index: 1250712 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4558. Min Act: -0.0001

Data Index: 788422 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4141. Min Act: -0.0001

Data Index: 1322014 (C4 (Web Text))

Max Activating Token Index: 922