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

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

Neuron 1937 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: 0.1537. Min Range: -0.1537

Max Act: 0.1526. Min Act: -0.0001

Data Index: 593459 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1537. Min Act: -0.0001

Data Index: 998690 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1296. Min Act: -0.0001

Data Index: 569281 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1321. Min Act: -0.0001

Data Index: 710027 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1327. Min Act: -0.0001

Data Index: 536055 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1236. Min Act: -0.0001

Data Index: 175111 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1092156 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1265. Min Act: -0.0001

Data Index: 403244 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1190038 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1155264 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1030375 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1214. Min Act: -0.0001

Data Index: 675772 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1242755 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1223. Min Act: -0.0001

Data Index: 901097 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1320. Min Act: -0.0001

Data Index: 695288 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1052493 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1139. Min Act: -0.0001

Data Index: 264520 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1206. Min Act: -0.0001

Data Index: 324198 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1173. Min Act: -0.0001

Data Index: 853188 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1125. Min Act: -0.0001

Data Index: 765912 (C4 (Web Text))

Max Activating Token Index: 569