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

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

Neuron 5565 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1937. Min Range: -4.1937

Max Act: 4.1937. Min Act: -0.0000

Data Index: 658838 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 4.1937. Min Range: -4.1937

Max Act: 3.7072. Min Act: -0.0000

Data Index: 1193383 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.9632. Min Act: -0.0000

Data Index: 823228 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 4.1937. Min Range: -4.1937

Max Act: 3.0679. Min Act: -0.0000

Data Index: 114126 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.8536. Min Act: -0.0000

Data Index: 254383 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.9941. Min Act: -0.0000

Data Index: 1077743 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.7046. Min Act: -0.0000

Data Index: 406751 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.6786. Min Act: -0.0000

Data Index: 881385 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.6119. Min Act: -0.0000

Data Index: 912504 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.6855. Min Act: -0.0000

Data Index: 393246 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.3928. Min Act: -0.0000

Data Index: 486244 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.3781. Min Act: -0.0000

Data Index: 955198 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.9138. Min Act: -0.0000

Data Index: 604023 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.5973. Min Act: -0.0000

Data Index: 1236337 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.8106. Min Act: -0.0000

Data Index: 909605 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.5482. Min Act: -0.0000

Data Index: 78246 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.1946. Min Act: -0.0000

Data Index: 858833 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.5339. Min Act: -0.0000

Data Index: 793305 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.3986. Min Act: -0.0000

Data Index: 956954 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 4.1937. Min Range: -4.1937

Max Act: 2.5052. Min Act: -0.0000

Data Index: 868415 (C4 (Web Text))

Max Activating Token Index: 172