Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2273 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.8513. Min Act: -0.0001

Data Index: 17095 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.8173. Min Act: -0.0001

Data Index: 465330 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7833. Min Act: -0.0001

Data Index: 187187 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7037. Min Act: -0.0001

Data Index: 545321 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7277. Min Act: -0.0001

Data Index: 923654 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6732. Min Act: -0.0001

Data Index: 426194 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7134. Min Act: -0.0001

Data Index: 942525 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7111. Min Act: -0.0001

Data Index: 313228 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6672. Min Act: -0.0001

Data Index: 405783 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6402. Min Act: -0.0001

Data Index: 492781 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.5646. Min Act: -0.0001

Data Index: 1282272 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6383. Min Act: -0.0001

Data Index: 268991 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6275. Min Act: -0.0001

Data Index: 995972 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6206. Min Act: -0.0001

Data Index: 508568 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6194. Min Act: -0.0001

Data Index: 58158 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6424. Min Act: -0.0001

Data Index: 491218 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6320. Min Act: -0.0001

Data Index: 98645 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6275. Min Act: -0.0001

Data Index: 178665 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6433. Min Act: -0.0001

Data Index: 1200231 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6104. Min Act: -0.0001

Data Index: 102800 (C4 (Web Text))

Max Activating Token Index: 681