Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1376 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1902. Min Act: -0.0001

Data Index: 603620 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1870. Min Act: -0.0001

Data Index: 887792 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1802. Min Act: -0.0001

Data Index: 234184 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1634. Min Act: -0.0001

Data Index: 676548 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1609. Min Act: -0.0001

Data Index: 2980 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1481. Min Act: -0.0001

Data Index: 10557 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1401. Min Act: -0.0001

Data Index: 760678 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1374. Min Act: -0.0001

Data Index: 1234721 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1415. Min Act: -0.0001

Data Index: 841880 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1355. Min Act: -0.0001

Data Index: 460735 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1278. Min Act: -0.0001

Data Index: 971274 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1235. Min Act: -0.0001

Data Index: 788777 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1298. Min Act: -0.0001

Data Index: 899352 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1287. Min Act: -0.0001

Data Index: 482924 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1247. Min Act: -0.0001

Data Index: 500039 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1223. Min Act: -0.0001

Data Index: 353550 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1253. Min Act: -0.0001

Data Index: 529225 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1272615 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1105371 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1251. Min Act: -0.0001

Data Index: 1220139 (C4 (Web Text))

Max Activating Token Index: 933