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

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

Neuron 783 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: 0.7442. Min Range: -0.7442

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1240117 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6306. Min Act: -0.0000

Data Index: 642406 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6508. Min Act: -0.0000

Data Index: 606082 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6346. Min Act: 0.0000

Data Index: 770371 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6395. Min Act: -0.0000

Data Index: 318186 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5909. Min Act: -0.0000

Data Index: 288518 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5546. Min Act: -0.0000

Data Index: 42398 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1043362 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5152. Min Act: -0.0000

Data Index: 558601 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1229414 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5217. Min Act: -0.0000

Data Index: 530015 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5062. Min Act: -0.0000

Data Index: 836674 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1274101 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1270178 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5092. Min Act: -0.0000

Data Index: 294593 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1208679 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.4862. Min Act: -0.0000

Data Index: 290274 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1236344 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.4864. Min Act: -0.0000

Data Index: 599646 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1129688 (C4 (Web Text))

Max Activating Token Index: 334