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

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

Neuron 1167 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.5823. Min Act: -0.0000

Data Index: 1008550 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.3155. Min Act: -0.0000

Data Index: 96971 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.3854. Min Act: -0.0000

Data Index: 1009355 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.3703. Min Act: -0.0000

Data Index: 951351 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.1000. Min Act: -0.0000

Data Index: 114947 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.0125. Min Act: -0.0000

Data Index: 915290 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.9767. Min Act: -0.0000

Data Index: 287811 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.8995. Min Act: -0.0000

Data Index: 18001 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1035241 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.7820. Min Act: -0.0000

Data Index: 587177 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1124922 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1136937 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.8259. Min Act: -0.0000

Data Index: 309069 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1060179 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.7826. Min Act: -0.0000

Data Index: 858876 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1141660 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.7380. Min Act: -0.0000

Data Index: 58883 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.7534. Min Act: -0.0000

Data Index: 264602 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.7937. Min Act: -0.0000

Data Index: 368132 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 1.5823. Min Range: -1.5823

Max Act: 0.6633. Min Act: -0.0000

Data Index: 599728 (C4 (Web Text))

Max Activating Token Index: 79