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

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

Neuron 2302 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.5614. Min Act: -0.0000

Data Index: 317722 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.5220. Min Act: -0.0000

Data Index: 812240 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4759. Min Act: -0.0000

Data Index: 493411 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1119031 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4589. Min Act: -0.0000

Data Index: 175690 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4469. Min Act: -0.0000

Data Index: 709172 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1313617 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4565. Min Act: -0.0000

Data Index: 795771 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4686. Min Act: -0.0000

Data Index: 773271 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4396. Min Act: -0.0000

Data Index: 860163 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4077. Min Act: -0.0000

Data Index: 320116 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4296. Min Act: 0.0000

Data Index: 1075545 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4488. Min Act: -0.0000

Data Index: 908738 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1358908 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1235863 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.3978. Min Act: -0.0000

Data Index: 692198 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4085. Min Act: -0.0000

Data Index: 632316 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4027. Min Act: -0.0000

Data Index: 838006 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.3932. Min Act: -0.0000

Data Index: 519217 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.3968. Min Act: -0.0000

Data Index: 505120 (C4 (Web Text))

Max Activating Token Index: 336