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

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

Neuron 3982 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5865. Min Act: -0.0000

Data Index: 482887 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5336. Min Act: -0.0000

Data Index: 996875 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1270069 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1340364 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5146. Min Act: -0.0000

Data Index: 874954 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5526. Min Act: -0.0000

Data Index: 189201 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4640. Min Act: -0.0000

Data Index: 966090 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4872. Min Act: -0.0000

Data Index: 726544 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4690. Min Act: -0.0000

Data Index: 850001 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4442. Min Act: -0.0000

Data Index: 721593 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4608. Min Act: -0.0000

Data Index: 615048 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4686. Min Act: -0.0000

Data Index: 655874 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1048377 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4629. Min Act: -0.0000

Data Index: 302136 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4726. Min Act: -0.0000

Data Index: 865028 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4607. Min Act: -0.0000

Data Index: 994787 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4249. Min Act: -0.0000

Data Index: 136147 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1148746 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1312573 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1175291 (C4 (Web Text))

Max Activating Token Index: 698