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

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

Neuron 2637 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: 2.1766. Min Range: -2.1766

Max Act: 2.1671. Min Act: -0.0000

Data Index: 923550 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 2.1766. Min Range: -2.1766

Max Act: 2.1766. Min Act: -0.0000

Data Index: 660035 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 2.1766. Min Range: -2.1766

Max Act: 2.0437. Min Act: -0.0000

Data Index: 652967 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 2.1766. Min Range: -2.1766

Max Act: 2.0866. Min Act: -0.0000

Data Index: 1229555 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 2.1766. Min Range: -2.1766

Max Act: 2.0897. Min Act: -0.0000

Data Index: 393375 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 2.1766. Min Range: -2.1766

Max Act: 2.0469. Min Act: -0.0000

Data Index: 865853 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.9552. Min Act: -0.0000

Data Index: 5067 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 2.1766. Min Range: -2.1766

Max Act: 2.0093. Min Act: -0.0000

Data Index: 14445 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.9930. Min Act: -0.0000

Data Index: 387786 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.7533. Min Act: -0.0000

Data Index: 122435 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.9594. Min Act: -0.0000

Data Index: 990548 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.7174. Min Act: -0.0000

Data Index: 975327 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.7948. Min Act: -0.0000

Data Index: 1157872 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.7820. Min Act: -0.0000

Data Index: 617216 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.7915. Min Act: -0.0000

Data Index: 1081187 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.7860. Min Act: -0.0000

Data Index: 651999 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1111366 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.7799. Min Act: -0.0000

Data Index: 296950 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.7218. Min Act: -0.0000

Data Index: 764393 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 2.1766. Min Range: -2.1766

Max Act: 1.6770. Min Act: -0.0000

Data Index: 324660 (C4 (Web Text))

Max Activating Token Index: 260