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

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

Neuron 1403 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: 1.5847. Min Range: -1.5847

Max Act: 1.5847. Min Act: -0.0000

Data Index: 229092 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.2829. Min Act: -0.0000

Data Index: 1067891 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.1785. Min Act: 0.0000

Data Index: 1208600 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.1345. Min Act: -0.0000

Data Index: 420570 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.0203. Min Act: -0.0000

Data Index: 929910 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.1160. Min Act: -0.0000

Data Index: 810865 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.0680. Min Act: -0.0000

Data Index: 925759 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.0878. Min Act: -0.0000

Data Index: 493936 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 1.5847. Min Range: -1.5847

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1408689 (Python Code)

Max Activating Token Index: 870

Text #9

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.0768. Min Act: 0.0000

Data Index: 671334 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1257104 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1141276 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.0322. Min Act: -0.0000

Data Index: 721986 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1407412 (Python Code)

Max Activating Token Index: 870

Text #14

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.0848. Min Act: -0.0000

Data Index: 612485 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.0150. Min Act: -0.0000

Data Index: 687489 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.0056. Min Act: -0.0000

Data Index: 495674 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 1.5847. Min Range: -1.5847

Max Act: 0.9972. Min Act: 0.0000

Data Index: 517198 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 1.5847. Min Range: -1.5847

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1267184 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 1.5847. Min Range: -1.5847

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1533373 (Python Code)

Max Activating Token Index: 653