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

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

Neuron 2690 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: 0.6311. Min Range: -0.6311

Max Act: 0.6311. Min Act: -0.0000

Data Index: 253957 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.6212. Min Act: -0.0000

Data Index: 721808 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.6100. Min Act: -0.0000

Data Index: 243078 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5902. Min Act: -0.0000

Data Index: 500692 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.6086. Min Act: -0.0000

Data Index: 337047 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1336533 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5734. Min Act: -0.0000

Data Index: 669589 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1092268 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1318238 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1137022 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4969. Min Act: -0.0000

Data Index: 176280 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.3804. Min Act: -0.0000

Data Index: 221669 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5130. Min Act: -0.0000

Data Index: 149064 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4595. Min Act: -0.0000

Data Index: 612148 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1187381 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4774. Min Act: -0.0000

Data Index: 721956 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4111. Min Act: -0.0000

Data Index: 895541 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1024355 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4090. Min Act: -0.0000

Data Index: 230342 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4347. Min Act: -0.0000

Data Index: 806902 (C4 (Web Text))

Max Activating Token Index: 499