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

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

Neuron 2199 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: 0.3145. Min Range: -0.3145

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1651417 (Python Code)

Max Activating Token Index: 532

Text #1

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1651120 (Python Code)

Max Activating Token Index: 826

Text #2

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1415775 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1380887 (Python Code)

Max Activating Token Index: 541

Text #4

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1412904 (Python Code)

Max Activating Token Index: 857

Text #5

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1633326 (Python Code)

Max Activating Token Index: 582

Text #6

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1589835 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2131. Min Act: -0.0000

Data Index: 198473 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1627887 (Python Code)

Max Activating Token Index: 581

Text #9

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2222. Min Act: -0.0000

Data Index: 269144 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1379942 (Python Code)

Max Activating Token Index: 955

Text #11

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1498954 (Python Code)

Max Activating Token Index: 544

Text #12

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1530104 (Python Code)

Max Activating Token Index: 531

Text #13

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2006. Min Act: -0.0000

Data Index: 368156 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1482025 (Python Code)

Max Activating Token Index: 232

Text #15

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1340370 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2053. Min Act: -0.0000

Data Index: 662451 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1459167 (Python Code)

Max Activating Token Index: 371

Text #18

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2044. Min Act: -0.0000

Data Index: 21368 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1953. Min Act: -0.0000

Data Index: 79854 (C4 (Web Text))

Max Activating Token Index: 221