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

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

Neuron 3024 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: 2.1075. Min Range: -2.1075

Max Act: 2.1075. Min Act: -0.0000

Data Index: 765586 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 2.1075. Min Range: -2.1075

Max Act: 2.0520. Min Act: -0.0000

Data Index: 1648192 (Python Code)

Max Activating Token Index: 1010

Text #2

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.8352. Min Act: -0.0000

Data Index: 475845 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.7995. Min Act: -0.0000

Data Index: 1502988 (Python Code)

Max Activating Token Index: 633

Text #4

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.6539. Min Act: -0.0000

Data Index: 1221348 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.6536. Min Act: -0.0000

Data Index: 1639459 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.5305. Min Act: -0.0000

Data Index: 366622 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.6173. Min Act: -0.0000

Data Index: 1550857 (Python Code)

Max Activating Token Index: 450

Text #8

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.6228. Min Act: -0.0000

Data Index: 1447255 (Python Code)

Max Activating Token Index: 309

Text #9

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.6047. Min Act: -0.0000

Data Index: 665797 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.5211. Min Act: -0.0000

Data Index: 725669 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.5925. Min Act: -0.0000

Data Index: 621727 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.4723. Min Act: -0.0000

Data Index: 580185 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.4729. Min Act: -0.0000

Data Index: 1384848 (Python Code)

Max Activating Token Index: 932

Text #14

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.4637. Min Act: -0.0000

Data Index: 779860 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.4493. Min Act: -0.0000

Data Index: 1506467 (Python Code)

Max Activating Token Index: 1008

Text #16

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.4549. Min Act: -0.0000

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1134325 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.5086. Min Act: -0.0000

Data Index: 54648 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 2.1075. Min Range: -2.1075

Max Act: 1.4973. Min Act: -0.0000

Data Index: 1506413 (Python Code)

Max Activating Token Index: 418