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

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

Neuron 1256 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.5700. Min Act: -0.0000

Data Index: 28377 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.5386. Min Act: -0.0000

Data Index: 4712 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.2617. Min Act: -0.0000

Data Index: 1082838 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.2397. Min Act: -0.0000

Data Index: 608598 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.3001. Min Act: -0.0000

Data Index: 755526 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1015654 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.2058. Min Act: -0.0000

Data Index: 647299 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.1688. Min Act: -0.0000

Data Index: 96513 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1112265 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.1354. Min Act: -0.0000

Data Index: 258085 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.0872. Min Act: -0.0000

Data Index: 664834 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.1315. Min Act: -0.0000

Data Index: 286599 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1319783 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.1113. Min Act: -0.0000

Data Index: 266774 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.1318. Min Act: -0.0000

Data Index: 468639 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.0116. Min Act: -0.0000

Data Index: 290461 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.0625. Min Act: -0.0000

Data Index: 839681 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.0542. Min Act: -0.0000

Data Index: 364525 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.0082. Min Act: -0.0000

Data Index: 873732 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.5700. Min Range: -1.5700

Max Act: 1.0330. Min Act: -0.0000

Data Index: 471580 (C4 (Web Text))

Max Activating Token Index: 886