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

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

Neuron 389 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5892. Min Act: -0.0000

Data Index: 558025 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6386. Min Act: -0.0000

Data Index: 569934 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1447390 (Python Code)

Max Activating Token Index: 723

Text #3

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5936. Min Act: -0.0000

Data Index: 492034 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5393. Min Act: -0.0000

Data Index: 478596 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5060. Min Act: -0.0000

Data Index: 583565 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5356. Min Act: -0.0000

Data Index: 306729 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1541733 (Python Code)

Max Activating Token Index: 267

Text #8

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1434368 (Python Code)

Max Activating Token Index: 624

Text #9

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1115512 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5480. Min Act: -0.0000

Data Index: 671208 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5072. Min Act: -0.0000

Data Index: 81747 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1342571 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4898. Min Act: -0.0000

Data Index: 407405 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4939. Min Act: -0.0000

Data Index: 5137 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1489116 (Python Code)

Max Activating Token Index: 937

Text #16

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1499715 (Python Code)

Max Activating Token Index: 466

Text #17

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1488153 (Python Code)

Max Activating Token Index: 849

Text #18

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4951. Min Act: -0.0000

Data Index: 641496 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4365. Min Act: -0.0000

Data Index: 618303 (C4 (Web Text))

Max Activating Token Index: 600