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

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

Neuron 3007 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: 0.6263. Min Range: -0.6263

Max Act: 0.5786. Min Act: -0.0000

Data Index: 255330 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1239707 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.6236. Min Act: -0.0000

Data Index: 921404 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.6109. Min Act: -0.0000

Data Index: 254818 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5904. Min Act: -0.0000

Data Index: 878767 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1166989 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5742. Min Act: -0.0000

Data Index: 833554 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5752. Min Act: -0.0000

Data Index: 648525 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.6106. Min Act: -0.0000

Data Index: 167398 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1265234 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5535. Min Act: -0.0000

Data Index: 181904 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5191. Min Act: -0.0000

Data Index: 777040 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5356. Min Act: -0.0000

Data Index: 920313 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5403. Min Act: -0.0000

Data Index: 827734 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5300. Min Act: 0.0000

Data Index: 1142905 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1494231 (Python Code)

Max Activating Token Index: 138

Text #16

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4870. Min Act: -0.0000

Data Index: 1392993 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1190825 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5118. Min Act: -0.0000

Data Index: 805858 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5080. Min Act: -0.0000

Data Index: 359309 (C4 (Web Text))

Max Activating Token Index: 61