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

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

Neuron 3938 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1108289 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.2538. Min Act: -0.0000

Data Index: 162249 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1633. Min Act: -0.0000

Data Index: 200254 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1690. Min Act: -0.0000

Data Index: 115164 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1104757 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1610. Min Act: -0.0000

Data Index: 721627 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1463. Min Act: -0.0000

Data Index: 305425 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1497. Min Act: -0.0000

Data Index: 759752 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1188098 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1447. Min Act: -0.0000

Data Index: 84720 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1503. Min Act: -0.0000

Data Index: 872992 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1604. Min Act: -0.0000

Data Index: 110229 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1236634 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1389. Min Act: -0.0000

Data Index: 613813 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1399. Min Act: -0.0000

Data Index: 134252 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1454. Min Act: -0.0000

Data Index: 330886 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1626908 (Python Code)

Max Activating Token Index: 81

Text #17

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1297. Min Act: -0.0000

Data Index: 883501 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1379. Min Act: -0.0000

Data Index: 636265 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.3042. Min Range: -0.3042

Max Act: 0.1491. Min Act: -0.0000

Data Index: 245721 (C4 (Web Text))

Max Activating Token Index: 306