Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 27 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1216413 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.6712. Min Act: -0.0000

Data Index: 651609 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.4982. Min Act: -0.0000

Data Index: 413432 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.4103. Min Act: -0.0000

Data Index: 158026 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.4789. Min Act: -0.0000

Data Index: 1026316 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.3758. Min Act: -0.0000

Data Index: 1207782 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.3305. Min Act: -0.0000

Data Index: 89091 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.3852. Min Act: -0.0000

Data Index: 1271666 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2595. Min Act: -0.0000

Data Index: 374072 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2483. Min Act: -0.0000

Data Index: 263469 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2484. Min Act: -0.0000

Data Index: 951532 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2000. Min Act: -0.0000

Data Index: 104817 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.1856. Min Act: -0.0000

Data Index: 193508 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2151. Min Act: -0.0000

Data Index: 808689 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.1744. Min Act: -0.0000

Data Index: 628972 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.1771. Min Act: -0.0000

Data Index: 380061 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2086. Min Act: -0.0000

Data Index: 1330874 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2677. Min Act: 0.0000

Data Index: 773873 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.1165. Min Act: -0.0000

Data Index: 4319 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2147. Min Act: -0.0000

Data Index: 1260355 (C4 (Web Text))

Max Activating Token Index: 361