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

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

Neuron 3531 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6649. Min Act: 0.0000

Data Index: 1351805 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1422151 (Python Code)

Max Activating Token Index: 244

Text #2

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1086778 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5299. Min Act: 0.0000

Data Index: 947682 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5311. Min Act: -0.0000

Data Index: 172857 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4945. Min Act: 0.0000

Data Index: 676624 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4989. Min Act: 0.0000

Data Index: 374573 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5094. Min Act: -0.0000

Data Index: 339738 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1342242 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1325014 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1072007 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4639. Min Act: -0.0000

Data Index: 259682 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4669. Min Act: -0.0000

Data Index: 500476 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4741. Min Act: -0.0000

Data Index: 927297 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1321377 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4192. Min Act: -0.0000

Data Index: 622495 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1522976 (Python Code)

Max Activating Token Index: 976

Text #17

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4065. Min Act: -0.0000

Data Index: 853994 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4027. Min Act: -0.0000

Data Index: 119806 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4016. Min Act: -0.0000

Data Index: 912426 (C4 (Web Text))

Max Activating Token Index: 481