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

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

Neuron 3557 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3479. Min Act: -0.0002

Data Index: 989563 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2585. Min Act: -0.0002

Data Index: 359577 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2752. Min Act: -0.0002

Data Index: 418244 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2398. Min Act: -0.0002

Data Index: 1340341 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2749. Min Act: -0.0002

Data Index: 30993 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2517. Min Act: -0.0002

Data Index: 337411 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2484. Min Act: -0.0002

Data Index: 77223 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2557. Min Act: -0.0002

Data Index: 586005 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2287. Min Act: -0.0002

Data Index: 637209 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2469. Min Act: -0.0002

Data Index: 552461 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2291. Min Act: -0.0002

Data Index: 1098851 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2120. Min Act: -0.0002

Data Index: 977623 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.1807. Min Act: -0.0002

Data Index: 133563 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2106. Min Act: -0.0002

Data Index: 1040678 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2078. Min Act: -0.0002

Data Index: 270927 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2125. Min Act: -0.0002

Data Index: 475536 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2274. Min Act: -0.0002

Data Index: 555376 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.1876. Min Act: -0.0002

Data Index: 1257888 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2058. Min Act: -0.0002

Data Index: 631133 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.2495. Min Act: -0.0002

Data Index: 1208000 (C4 (Web Text))

Max Activating Token Index: 250