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

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

Neuron 3780 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1083587 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9600. Min Act: -0.0000

Data Index: 132976 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.8002. Min Act: -0.0000

Data Index: 760394 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9206. Min Act: -0.0000

Data Index: 661147 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1155675 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1393736 (Python Code)

Max Activating Token Index: 134

Text #6

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1108711 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1269027 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1587924 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.7962. Min Act: -0.0000

Data Index: 745538 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.8645. Min Act: -0.0000

Data Index: 522602 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.7495. Min Act: -0.0000

Data Index: 648925 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.7588. Min Act: -0.0000

Data Index: 119360 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1400892 (Python Code)

Max Activating Token Index: 486

Text #14

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1113461 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.7992. Min Act: -0.0000

Data Index: 724959 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1419549 (Python Code)

Max Activating Token Index: 518

Text #17

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1459476 (Python Code)

Max Activating Token Index: 403

Text #18

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1304216 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.8035. Min Act: -0.0000

Data Index: 126877 (C4 (Web Text))

Max Activating Token Index: 274