Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1429 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2717. Min Act: -0.0000

Data Index: 3094 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2778. Min Act: -0.0000

Data Index: 33742 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2319. Min Act: -0.0000

Data Index: 27647 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2551. Min Act: -0.0000

Data Index: 351819 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2556. Min Act: -0.0001

Data Index: 68103 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2127. Min Act: -0.0001

Data Index: 860891 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1261981 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2128. Min Act: -0.0000

Data Index: 125185 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2270. Min Act: -0.0001

Data Index: 317121 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2353. Min Act: -0.0000

Data Index: 221243 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1070152 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2154. Min Act: -0.0000

Data Index: 630414 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1072295 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2385. Min Act: -0.0001

Data Index: 222948 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2267. Min Act: -0.0000

Data Index: 900056 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1911. Min Act: -0.0000

Data Index: 806705 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2221. Min Act: -0.0000

Data Index: 515491 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2317. Min Act: -0.0000

Data Index: 241767 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1204040 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1116310 (C4 (Web Text))

Max Activating Token Index: 563