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

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

Neuron 3703 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2651. Min Range: -2.2651

Max Act: 2.2651. Min Act: -0.0000

Data Index: 989633 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.6598. Min Act: -0.0000

Data Index: 781217 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.6159. Min Act: -0.0000

Data Index: 719118 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.3136. Min Act: -0.0000

Data Index: 444378 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.3859. Min Act: -0.0000

Data Index: 456635 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.3015. Min Act: -0.0000

Data Index: 630996 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.3366. Min Act: -0.0000

Data Index: 89536 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.2639. Min Act: -0.0000

Data Index: 518016 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.2572. Min Act: -0.0000

Data Index: 144911 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.1749. Min Act: -0.0000

Data Index: 969523 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1080993 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.2063. Min Act: -0.0000

Data Index: 648316 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.1418. Min Act: -0.0000

Data Index: 842170 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.1346. Min Act: -0.0000

Data Index: 813142 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1261432 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.0843. Min Act: -0.0000

Data Index: 460505 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.0909. Min Act: -0.0000

Data Index: 455449 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.1565. Min Act: -0.0000

Data Index: 861864 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.1507. Min Act: -0.0000

Data Index: 1190873 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 2.2651. Min Range: -2.2651

Max Act: 1.0940. Min Act: -0.0000

Data Index: 90781 (C4 (Web Text))

Max Activating Token Index: 98