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

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

Neuron 2417 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.2153. Min Act: -0.0001

Data Index: 640944 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1987. Min Act: -0.0001

Data Index: 708755 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1995. Min Act: -0.0001

Data Index: 1285496 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1826. Min Act: -0.0001

Data Index: 999374 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1984. Min Act: -0.0001

Data Index: 81247 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1638. Min Act: -0.0001

Data Index: 668302 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1720. Min Act: -0.0001

Data Index: 962351 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1585. Min Act: -0.0001

Data Index: 321216 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1504. Min Act: -0.0001

Data Index: 1128839 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1618. Min Act: -0.0001

Data Index: 950158 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1514. Min Act: -0.0001

Data Index: 139464 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1285569 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1530. Min Act: -0.0001

Data Index: 297482 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1468. Min Act: -0.0000

Data Index: 286251 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1075907 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1541. Min Act: -0.0001

Data Index: 874152 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1527. Min Act: -0.0001

Data Index: 150590 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1469. Min Act: -0.0000

Data Index: 474860 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1258284 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1525. Min Act: -0.0001

Data Index: 423541 (C4 (Web Text))

Max Activating Token Index: 579