Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4156 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1489. Min Act: -0.0000

Data Index: 33295 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1444. Min Act: -0.0000

Data Index: 625476 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1372. Min Act: -0.0000

Data Index: 520710 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1334. Min Act: -0.0000

Data Index: 837971 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1259. Min Act: -0.0000

Data Index: 105775 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1023842 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1326. Min Act: -0.0000

Data Index: 234439 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1112482 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1211. Min Act: -0.0000

Data Index: 236544 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1192. Min Act: -0.0000

Data Index: 260793 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1230. Min Act: -0.0000

Data Index: 801261 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1291. Min Act: -0.0000

Data Index: 105626 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1276. Min Act: -0.0000

Data Index: 20729 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1296720 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1260. Min Act: -0.0000

Data Index: 897913 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1103308 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1286978 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1028. Min Act: -0.0000

Data Index: 364647 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1146. Min Act: -0.0000

Data Index: 497853 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1034. Min Act: -0.0000

Data Index: 670401 (C4 (Web Text))

Max Activating Token Index: 457