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

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

Neuron 1799 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2226. Min Act: -0.0000

Data Index: 60234 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1249448 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1145339 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2174. Min Act: -0.0000

Data Index: 468942 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1937. Min Act: -0.0000

Data Index: 480092 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2154. Min Act: -0.0000

Data Index: 167987 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2053. Min Act: -0.0000

Data Index: 905917 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2026. Min Act: -0.0000

Data Index: 571870 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1018051 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1802. Min Act: -0.0000

Data Index: 368317 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1896. Min Act: -0.0000

Data Index: 265848 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1886. Min Act: -0.0000

Data Index: 785493 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1872. Min Act: -0.0000

Data Index: 705620 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1957. Min Act: -0.0000

Data Index: 288702 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1713. Min Act: -0.0000

Data Index: 290545 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1116382 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1592. Min Act: -0.0000

Data Index: 515290 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1198849 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1778. Min Act: -0.0000

Data Index: 562225 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1338955 (C4 (Web Text))

Max Activating Token Index: 340