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

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

Neuron 4855 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3544. Min Act: -0.0003

Data Index: 302424 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3444. Min Act: -0.0003

Data Index: 613615 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3500. Min Act: -0.0003

Data Index: 907298 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3343. Min Act: -0.0003

Data Index: 1074895 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3259. Min Act: -0.0003

Data Index: 1125056 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3120. Min Act: -0.0003

Data Index: 976212 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3071. Min Act: -0.0003

Data Index: 1201090 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3143. Min Act: -0.0003

Data Index: 883432 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2712. Min Act: -0.0003

Data Index: 957643 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.1433. Min Act: -0.0002

Data Index: 1581747 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.1433. Min Act: -0.0003

Data Index: 1572094 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.1477. Min Act: -0.0002

Data Index: 1525631 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.1477. Min Act: -0.0002

Data Index: 1404768 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.1436. Min Act: -0.0002

Data Index: 1601221 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.1436. Min Act: -0.0002

Data Index: 1575205 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1401323 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1507576 (Python Code)

Max Activating Token Index: 13

Text #17

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.1335. Min Act: -0.0002

Data Index: 1645749 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.1246. Min Act: -0.0002

Data Index: 1475768 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.1246. Min Act: -0.0002

Data Index: 1563116 (Python Code)

Max Activating Token Index: 18