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

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

Neuron 3076 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1628. Min Act: -0.0000

Data Index: 435246 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1133158 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1140711 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1448537 (Python Code)

Max Activating Token Index: 771

Text #4

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1236. Min Act: -0.0000

Data Index: 297533 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1451489 (Python Code)

Max Activating Token Index: 618

Text #6

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.3394. Min Act: -0.0000

Data Index: 621395 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1174. Min Act: -0.0000

Data Index: 1049230 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1096. Min Act: -0.0000

Data Index: 752239 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1100384 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1165. Min Act: -0.0000

Data Index: 733321 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1143. Min Act: -0.0000

Data Index: 569854 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1646460 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1110. Min Act: -0.0000

Data Index: 672895 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1055895 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1519527 (Python Code)

Max Activating Token Index: 818

Text #16

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1580873 (Python Code)

Max Activating Token Index: 836

Text #17

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1295112 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1457366 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.0978. Min Act: -0.0000

Data Index: 677124 (C4 (Web Text))

Max Activating Token Index: 189