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

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

Neuron 4757 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1576. Min Range: -7.1576

Max Act: 7.1323. Min Act: -0.0000

Data Index: 1117315 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 7.1576. Min Range: -7.1576

Max Act: 7.1167. Min Act: -0.0000

Data Index: 453240 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.8450. Min Act: -0.0000

Data Index: 457935 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 7.1576. Min Range: -7.1576

Max Act: 7.1576. Min Act: -0.0000

Data Index: 1295621 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.9328. Min Act: -0.0000

Data Index: 1289316 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.8684. Min Act: -0.0000

Data Index: 65995 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.7615. Min Act: -0.0000

Data Index: 1172069 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.9373. Min Act: -0.0000

Data Index: 72546 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.9011. Min Act: -0.0000

Data Index: 166656 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.8834. Min Act: -0.0000

Data Index: 508997 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.8680. Min Act: -0.0000

Data Index: 518564 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.4855. Min Act: -0.0000

Data Index: 170392 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.6890. Min Act: -0.0000

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.7694. Min Act: -0.0000

Data Index: 338553 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.7583. Min Act: -0.0000

Data Index: 723807 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.5539. Min Act: -0.0000

Data Index: 813467 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.7349. Min Act: -0.0000

Data Index: 533055 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.7409. Min Act: -0.0000

Data Index: 66368 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.5187. Min Act: -0.0000

Data Index: 1028625 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 7.1576. Min Range: -7.1576

Max Act: 6.6908. Min Act: -0.0000

Data Index: 137173 (C4 (Web Text))

Max Activating Token Index: 870