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

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

Neuron 3044 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.0933. Min Act: -0.0000

Data Index: 553245 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.9352. Min Act: -0.0000

Data Index: 1190332 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.4664. Min Act: -0.0001

Data Index: 804846 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.2093. Min Act: -0.0001

Data Index: 246254 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.8482. Min Act: -0.0001

Data Index: 1337609 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.7340. Min Act: -0.0000

Data Index: 1152900 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.7291. Min Act: -0.0001

Data Index: 1102304 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.7170. Min Act: -0.0001

Data Index: 1252308 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.4833. Min Act: -0.0000

Data Index: 705068 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.5895. Min Act: -0.0001

Data Index: 1005705 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.5375. Min Act: -0.0000

Data Index: 709062 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.5267. Min Act: -0.0001

Data Index: 7878 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.6524. Min Act: -0.0000

Data Index: 522525 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.3547. Min Act: -0.0000

Data Index: 1304196 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.4697. Min Act: -0.0000

Data Index: 1125629 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.2894. Min Act: -0.0000

Data Index: 1021935 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.6244. Min Act: -0.0000

Data Index: 842985 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.3836. Min Act: -0.0001

Data Index: 868966 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.3761. Min Act: -0.0000

Data Index: 169109 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 3.4664. Min Range: -3.4664

Max Act: 2.4940. Min Act: -0.0000

Data Index: 558275 (C4 (Web Text))

Max Activating Token Index: 967