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

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

Neuron 1207 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: 0.2662. Min Range: -0.2662

Max Act: 0.2662. Min Act: -0.0001

Data Index: 406500 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2649. Min Act: -0.0001

Data Index: 180602 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2519. Min Act: -0.0001

Data Index: 1062784 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2387. Min Act: -0.0001

Data Index: 507182 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2343. Min Act: -0.0001

Data Index: 868257 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2137. Min Act: -0.0001

Data Index: 49026 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2206. Min Act: -0.0001

Data Index: 49831 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2109. Min Act: -0.0001

Data Index: 1138605 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2223. Min Act: -0.0001

Data Index: 119325 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2226. Min Act: -0.0001

Data Index: 260412 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2024. Min Act: -0.0001

Data Index: 551288 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2181. Min Act: -0.0001

Data Index: 718188 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2084. Min Act: -0.0001

Data Index: 902582 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.1971. Min Act: -0.0001

Data Index: 650606 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2035. Min Act: -0.0001

Data Index: 918973 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.1993. Min Act: -0.0001

Data Index: 325575 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.1848. Min Act: -0.0001

Data Index: 868722 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.1895. Min Act: -0.0001

Data Index: 390580 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2034. Min Act: -0.0001

Data Index: 1255761 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.1948. Min Act: -0.0001

Data Index: 807277 (C4 (Web Text))

Max Activating Token Index: 844