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

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

Neuron 990 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: 0.1884. Min Range: -0.1884

Max Act: 0.1884. Min Act: -0.0001

Data Index: 867351 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1470374 (Python Code)

Max Activating Token Index: 430

Text #2

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1130915 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1297178 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1373574 (Python Code)

Max Activating Token Index: 489

Text #5

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1394. Min Act: -0.0001

Data Index: 1465210 (Python Code)

Max Activating Token Index: 415

Text #6

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1328. Min Act: -0.0001

Data Index: 921433 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1304. Min Act: -0.0001

Data Index: 1089328 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1361811 (Python Code)

Max Activating Token Index: 739

Text #9

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1550796 (Python Code)

Max Activating Token Index: 853

Text #10

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1331. Min Act: -0.0001

Data Index: 98406 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1579063 (Python Code)

Max Activating Token Index: 250

Text #12

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1197. Min Act: -0.0001

Data Index: 27004 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1208. Min Act: -0.0001

Data Index: 876095 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1576217 (Python Code)

Max Activating Token Index: 318

Text #15

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1072. Min Act: -0.0001

Data Index: 277979 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1249. Min Act: -0.0001

Data Index: 633303 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1360. Min Act: -0.0001

Data Index: 484671 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1228. Min Act: -0.0001

Data Index: 661769 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1095. Min Act: -0.0001

Data Index: 843082 (C4 (Web Text))

Max Activating Token Index: 851