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

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

Neuron 890 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.3480. Min Act: -0.0002

Data Index: 1164879 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.2236. Min Act: -0.0002

Data Index: 75519 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.2931. Min Act: -0.0002

Data Index: 524633 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.1908. Min Act: -0.0002

Data Index: 26849 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.2451. Min Act: -0.0002

Data Index: 1227955 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0565. Min Act: -0.0002

Data Index: 295509 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.1324. Min Act: -0.0002

Data Index: 221444 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0551. Min Act: -0.0002

Data Index: 373645 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.1092. Min Act: -0.0002

Data Index: 1342860 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0970. Min Act: -0.0002

Data Index: 1246890 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9734. Min Act: -0.0002

Data Index: 2797 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9989. Min Act: -0.0002

Data Index: 103875 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0574. Min Act: -0.0002

Data Index: 629178 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0847. Min Act: -0.0002

Data Index: 1115262 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.1040. Min Act: -0.0002

Data Index: 298714 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0620. Min Act: -0.0002

Data Index: 695882 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9101. Min Act: -0.0002

Data Index: 1090950 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0578. Min Act: -0.0002

Data Index: 805346 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0238. Min Act: -0.0002

Data Index: 399142 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9335. Min Act: -0.0002

Data Index: 1125272 (C4 (Web Text))

Max Activating Token Index: 565