Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 807 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.3083. Min Act: -0.0000

Data Index: 127973 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2882. Min Act: -0.0000

Data Index: 76895 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1938. Min Act: -0.0000

Data Index: 932959 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1850. Min Act: -0.0000

Data Index: 711211 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1257453 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1761. Min Act: -0.0000

Data Index: 212905 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1418101 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1568. Min Act: -0.0000

Data Index: 879574 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1108310 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1592. Min Act: -0.0000

Data Index: 619810 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1237208 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1521. Min Act: -0.0000

Data Index: 257516 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1469. Min Act: -0.0000

Data Index: 52056 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1456. Min Act: -0.0000

Data Index: 692918 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1282828 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1218843 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1411. Min Act: -0.0000

Data Index: 214900 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1341931 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1216372 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1460. Min Act: -0.0000

Data Index: 236815 (C4 (Web Text))

Max Activating Token Index: 57