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

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

Neuron 756 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0668. Min Act: -0.0003

Data Index: 595140 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0571. Min Act: -0.0002

Data Index: 567130 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0544. Min Act: -0.0002

Data Index: 503888 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0538. Min Act: -0.0003

Data Index: 1131186 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1329693 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0479. Min Act: -0.0002

Data Index: 38180 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0455. Min Act: -0.0003

Data Index: 447782 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1006831 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0467. Min Act: -0.0002

Data Index: 592577 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0448. Min Act: -0.0002

Data Index: 516771 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1170676 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0448. Min Act: -0.0003

Data Index: 785452 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0446. Min Act: -0.0003

Data Index: 844105 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0438. Min Act: -0.0002

Data Index: 296792 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0422. Min Act: -0.0002

Data Index: 483657 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0423. Min Act: -0.0002

Data Index: 126114 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1011137 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1033319 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0403. Min Act: -0.0002

Data Index: 189175 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0404. Min Act: -0.0002

Data Index: 357534 (C4 (Web Text))

Max Activating Token Index: 453