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

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

Neuron 5988 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.2610. Min Act: -0.0001

Data Index: 416466 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.4354. Min Act: -0.0000

Data Index: 870810 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 7.5085. Min Range: -7.5085

Max Act: 6.8986. Min Act: -0.0000

Data Index: 395139 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.3005. Min Act: -0.0000

Data Index: 1031274 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.5085. Min Act: -0.0000

Data Index: 4994 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.1071. Min Act: -0.0001

Data Index: 343670 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 7.5085. Min Range: -7.5085

Max Act: 6.5685. Min Act: -0.0000

Data Index: 1281431 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 7.5085. Min Range: -7.5085

Max Act: 6.6857. Min Act: -0.0000

Data Index: 264399 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.3565. Min Act: -0.0001

Data Index: 195170 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.2103. Min Act: -0.0000

Data Index: 1278312 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 7.5085. Min Range: -7.5085

Max Act: 6.4977. Min Act: -0.0001

Data Index: 1019989 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 7.5085. Min Range: -7.5085

Max Act: 6.1229. Min Act: -0.0000

Data Index: 1103398 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.1447. Min Act: -0.0001

Data Index: 361502 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.1699. Min Act: -0.0000

Data Index: 190548 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 7.5085. Min Range: -7.5085

Max Act: 6.9617. Min Act: -0.0000

Data Index: 774503 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.2010. Min Act: -0.0000

Data Index: 205887 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 7.5085. Min Range: -7.5085

Max Act: 6.3325. Min Act: -0.0000

Data Index: 929116 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.0464. Min Act: -0.0001

Data Index: 390822 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 7.5085. Min Range: -7.5085

Max Act: 7.0492. Min Act: -0.0001

Data Index: 1256270 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 7.5085. Min Range: -7.5085

Max Act: 6.9980. Min Act: -0.0000

Data Index: 972569 (C4 (Web Text))

Max Activating Token Index: 288