Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2977 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1194. Min Act: -0.0001

Data Index: 307100 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1109705 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0943. Min Act: -0.0001

Data Index: 360484 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1003. Min Act: -0.0001

Data Index: 32190 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1013074 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0935. Min Act: -0.0001

Data Index: 92943 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0939. Min Act: -0.0000

Data Index: 584340 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0913. Min Act: -0.0001

Data Index: 667287 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1174312 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1282526 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1138963 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0769. Min Act: -0.0001

Data Index: 512520 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1159221 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0820. Min Act: -0.0001

Data Index: 786767 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0887. Min Act: -0.0001

Data Index: 776952 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0790. Min Act: -0.0001

Data Index: 7641 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0733. Min Act: -0.0001

Data Index: 181615 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1422777 (Python Code)

Max Activating Token Index: 581

Text #18

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0758. Min Act: -0.0001

Data Index: 515834 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0835. Min Act: -0.0001

Data Index: 388359 (C4 (Web Text))

Max Activating Token Index: 938