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

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

Neuron 5614 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.0132. Min Range: -11.0132

Max Act: 11.0132. Min Act: -0.0000

Data Index: 291616 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 11.0132. Min Range: -11.0132

Max Act: 9.3891. Min Act: -0.0000

Data Index: 11229 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 11.0132. Min Range: -11.0132

Max Act: 8.4133. Min Act: -0.0000

Data Index: 744894 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 11.0132. Min Range: -11.0132

Max Act: 8.0084. Min Act: -0.0000

Data Index: 168703 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 11.0132. Min Range: -11.0132

Max Act: 7.7301. Min Act: -0.0000

Data Index: 1286174 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 11.0132. Min Range: -11.0132

Max Act: 6.9673. Min Act: -0.0000

Data Index: 1312153 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 11.0132. Min Range: -11.0132

Max Act: 6.7265. Min Act: -0.0000

Data Index: 425402 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 11.0132. Min Range: -11.0132

Max Act: 7.0179. Min Act: -0.0000

Data Index: 132016 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 11.0132. Min Range: -11.0132

Max Act: 6.4238. Min Act: -0.0000

Data Index: 228172 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 11.0132. Min Range: -11.0132

Max Act: 5.9915. Min Act: -0.0000

Data Index: 1165640 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 11.0132. Min Range: -11.0132

Max Act: 6.3822. Min Act: -0.0000

Data Index: 1021661 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 11.0132. Min Range: -11.0132

Max Act: 5.7218. Min Act: -0.0000

Data Index: 927461 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 11.0132. Min Range: -11.0132

Max Act: 5.6095. Min Act: -0.0000

Data Index: 1020170 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 11.0132. Min Range: -11.0132

Max Act: 5.5772. Min Act: -0.0000

Data Index: 1023907 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 11.0132. Min Range: -11.0132

Max Act: 5.9019. Min Act: -0.0000

Data Index: 1124664 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 11.0132. Min Range: -11.0132

Max Act: 5.6818. Min Act: -0.0000

Data Index: 1347942 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 11.0132. Min Range: -11.0132

Max Act: 5.4485. Min Act: -0.0000

Data Index: 310249 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 11.0132. Min Range: -11.0132

Max Act: 6.2203. Min Act: -0.0000

Data Index: 723484 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 11.0132. Min Range: -11.0132

Max Act: 5.1280. Min Act: -0.0000

Data Index: 626186 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 11.0132. Min Range: -11.0132

Max Act: 5.3555. Min Act: -0.0000

Data Index: 365937 (C4 (Web Text))

Max Activating Token Index: 153