Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4013 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0434. Min Range: -1.0434

Max Act: 1.0434. Min Act: -0.0001

Data Index: 1407285 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9220. Min Act: -0.0001

Data Index: 1618040 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8040. Min Act: -0.0001

Data Index: 1505102 (Python Code)

Max Activating Token Index: 826

Text #3

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.7392. Min Act: -0.0001

Data Index: 912617 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.7632. Min Act: -0.0001

Data Index: 96434 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.7115. Min Act: -0.0001

Data Index: 1568724 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.7884. Min Act: -0.0001

Data Index: 943770 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.6943. Min Act: -0.0001

Data Index: 1122944 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.7149. Min Act: -0.0001

Data Index: 803006 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.7332. Min Act: -0.0001

Data Index: 614672 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.7175. Min Act: -0.0001

Data Index: 545953 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.7078. Min Act: -0.0001

Data Index: 1382461 (Python Code)

Max Activating Token Index: 109

Text #12

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.6653. Min Act: -0.0001

Data Index: 137464 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.6420. Min Act: -0.0001

Data Index: 1028262 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.7008. Min Act: -0.0001

Data Index: 1211662 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.6749. Min Act: -0.0001

Data Index: 982884 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.7083. Min Act: -0.0001

Data Index: 1245238 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.6612. Min Act: -0.0001

Data Index: 564309 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.6631. Min Act: -0.0001

Data Index: 934236 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.6384. Min Act: -0.0001

Data Index: 1368740 (Python Code)

Max Activating Token Index: 246