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

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

Neuron 4695 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1861. Min Act: -0.0000

Data Index: 587045 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1395. Min Act: -0.0000

Data Index: 242224 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1447. Min Act: -0.0000

Data Index: 862395 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1401. Min Act: -0.0000

Data Index: 324217 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1422. Min Act: -0.0000

Data Index: 449272 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1320. Min Act: -0.0000

Data Index: 234833 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1509677 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1602104 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1115. Min Act: -0.0000

Data Index: 721898 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1132. Min Act: -0.0000

Data Index: 371927 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1317228 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1272855 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1588028 (Python Code)

Max Activating Token Index: 648

Text #13

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1319701 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1214700 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1196. Min Act: -0.0000

Data Index: 236439 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1163. Min Act: -0.0000

Data Index: 225506 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1076. Min Act: -0.0000

Data Index: 171858 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1103. Min Act: -0.0000

Data Index: 959023 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1041. Min Act: -0.0000

Data Index: 328368 (C4 (Web Text))

Max Activating Token Index: 785