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

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

Neuron 1315 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1222429 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5352. Min Act: -0.0000

Data Index: 714842 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5441. Min Act: -0.0000

Data Index: 119582 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5267. Min Act: -0.0000

Data Index: 397772 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4596. Min Act: -0.0000

Data Index: 919111 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4436. Min Act: -0.0000

Data Index: 491716 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4607. Min Act: -0.0000

Data Index: 757601 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1038366 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4724. Min Act: -0.0000

Data Index: 889238 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4522. Min Act: -0.0000

Data Index: 541775 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4588. Min Act: -0.0000

Data Index: 471069 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1054335 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3672. Min Act: -0.0000

Data Index: 127281 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1609642 (Python Code)

Max Activating Token Index: 832

Text #14

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1177790 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3680. Min Act: -0.0000

Data Index: 18978 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3847. Min Act: -0.0000

Data Index: 733935 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3345. Min Act: -0.0000

Data Index: 200692 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3195. Min Act: -0.0000

Data Index: 952844 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3624. Min Act: -0.0000

Data Index: 945544 (C4 (Web Text))

Max Activating Token Index: 339