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

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

Neuron 2590 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1194853 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5501. Min Act: -0.0000

Data Index: 289366 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5352. Min Act: -0.0000

Data Index: 113182 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5069. Min Act: -0.0000

Data Index: 701675 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4540. Min Act: -0.0000

Data Index: 641553 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4545. Min Act: -0.0000

Data Index: 168831 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4387. Min Act: -0.0000

Data Index: 672813 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4679. Min Act: 0.0000

Data Index: 128406 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4594. Min Act: -0.0000

Data Index: 256081 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4233. Min Act: -0.0000

Data Index: 744661 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4356. Min Act: -0.0000

Data Index: 995963 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1018467 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4186. Min Act: -0.0000

Data Index: 447314 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4567. Min Act: -0.0000

Data Index: 165328 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4284. Min Act: -0.0000

Data Index: 386149 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4322. Min Act: -0.0000

Data Index: 776735 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4010. Min Act: -0.0000

Data Index: 842153 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1281981 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4074. Min Act: -0.0000

Data Index: 641996 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1041553 (C4 (Web Text))

Max Activating Token Index: 15