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

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

Neuron 4285 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2640. Min Act: -0.0000

Data Index: 863758 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1005683 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2474. Min Act: -0.0000

Data Index: 718421 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2433. Min Act: -0.0000

Data Index: 458723 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2529. Min Act: -0.0000

Data Index: 349043 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1011487 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2447. Min Act: -0.0000

Data Index: 598935 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2380. Min Act: -0.0000

Data Index: 525073 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2362. Min Act: -0.0000

Data Index: 334092 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1130534 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2339. Min Act: -0.0000

Data Index: 971500 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2132. Min Act: -0.0000

Data Index: 483971 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1274414 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2063. Min Act: -0.0000

Data Index: 204875 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1171020 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.1976. Min Act: -0.0000

Data Index: 322843 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2072. Min Act: -0.0000

Data Index: 272314 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.1998. Min Act: -0.0000

Data Index: 86021 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1243586 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.1968. Min Act: 0.0000

Data Index: 786944 (C4 (Web Text))

Max Activating Token Index: 462