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

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

Neuron 5795 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: 1.1055. Min Range: -1.1055

Max Act: 1.1055. Min Act: -0.0000

Data Index: 1210305 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 1.1055. Min Range: -1.1055

Max Act: 1.0646. Min Act: -0.0000

Data Index: 206638 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.9059. Min Act: -0.0000

Data Index: 869361 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.8992. Min Act: -0.0000

Data Index: 374034 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.8780. Min Act: -0.0000

Data Index: 118484 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1078122 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.8062. Min Act: -0.0000

Data Index: 316758 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.8034. Min Act: -0.0000

Data Index: 967879 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7828. Min Act: -0.0000

Data Index: 1142715 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1323301 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7764. Min Act: -0.0000

Data Index: 589877 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7219. Min Act: -0.0000

Data Index: 180983 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.8108. Min Act: -0.0000

Data Index: 900873 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7353. Min Act: -0.0000

Data Index: 838329 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7540. Min Act: -0.0000

Data Index: 861033 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7477. Min Act: -0.0000

Data Index: 184880 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1125631 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7060. Min Act: -0.0000

Data Index: 581577 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7235. Min Act: -0.0000

Data Index: 305023 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7263. Min Act: -0.0000

Data Index: 986993 (C4 (Web Text))

Max Activating Token Index: 197