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

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

Neuron 2402 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: 6.2567. Min Range: -6.2567

Max Act: 6.2567. Min Act: -0.0000

Data Index: 1138322 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 6.2567. Min Range: -6.2567

Max Act: 5.9881. Min Act: -0.0000

Data Index: 1253557 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 6.2567. Min Range: -6.2567

Max Act: 5.7861. Min Act: -0.0000

Data Index: 288719 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 6.2567. Min Range: -6.2567

Max Act: 5.3886. Min Act: -0.0000

Data Index: 1034713 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 6.2567. Min Range: -6.2567

Max Act: 5.1562. Min Act: -0.0000

Data Index: 998042 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 6.2567. Min Range: -6.2567

Max Act: 5.2529. Min Act: -0.0000

Data Index: 296963 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 6.2567. Min Range: -6.2567

Max Act: 4.9029. Min Act: -0.0000

Data Index: 1053256 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 6.2567. Min Range: -6.2567

Max Act: 4.9914. Min Act: -0.0000

Data Index: 690478 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 6.2567. Min Range: -6.2567

Max Act: 5.0581. Min Act: -0.0000

Data Index: 921034 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 6.2567. Min Range: -6.2567

Max Act: 5.1951. Min Act: -0.0000

Data Index: 282651 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 6.2567. Min Range: -6.2567

Max Act: 5.0082. Min Act: -0.0000

Data Index: 572351 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 6.2567. Min Range: -6.2567

Max Act: 4.8277. Min Act: -0.0000

Data Index: 487896 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 6.2567. Min Range: -6.2567

Max Act: 4.8842. Min Act: -0.0000

Data Index: 1106759 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 6.2567. Min Range: -6.2567

Max Act: 4.8871. Min Act: -0.0000

Data Index: 240404 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 6.2567. Min Range: -6.2567

Max Act: 4.8998. Min Act: -0.0000

Data Index: 1055346 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 6.2567. Min Range: -6.2567

Max Act: 4.7640. Min Act: -0.0001

Data Index: 466316 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 6.2567. Min Range: -6.2567

Max Act: 5.0453. Min Act: -0.0000

Data Index: 1225200 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 6.2567. Min Range: -6.2567

Max Act: 5.0081. Min Act: -0.0000

Data Index: 1055590 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 6.2567. Min Range: -6.2567

Max Act: 5.0242. Min Act: -0.0000

Data Index: 1303202 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 6.2567. Min Range: -6.2567

Max Act: 4.4403. Min Act: -0.0000

Data Index: 333884 (C4 (Web Text))

Max Activating Token Index: 981