Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4916. Min Act: -0.0000

Data Index: 382434 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.2669. Min Act: -0.0001

Data Index: 582008 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.2120. Min Act: -0.0001

Data Index: 1178534 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.1460. Min Act: -0.0000

Data Index: 885103 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.0981. Min Act: -0.0000

Data Index: 1171546 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.0798. Min Act: -0.0000

Data Index: 1003652 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1224337 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1057223 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1200633 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.9198. Min Act: -0.0000

Data Index: 507005 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.9672. Min Act: -0.0000

Data Index: 906856 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1255711 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.9657. Min Act: -0.0000

Data Index: 619435 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8950. Min Act: -0.0000

Data Index: 588205 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8866. Min Act: -0.0000

Data Index: 151050 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8777. Min Act: -0.0000

Data Index: 739452 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8754. Min Act: -0.0000

Data Index: 779680 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8691. Min Act: -0.0001

Data Index: 540482 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1324942 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8678. Min Act: -0.0000

Data Index: 970648 (C4 (Web Text))

Max Activating Token Index: 701