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

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

Neuron 1048 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4810. Min Range: -2.4810

Max Act: 2.4810. Min Act: -0.0000

Data Index: 597083 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 2.4810. Min Range: -2.4810

Max Act: 2.2384. Min Act: -0.0000

Data Index: 315869 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 2.4810. Min Range: -2.4810

Max Act: 2.3405. Min Act: -0.0000

Data Index: 240526 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 2.4810. Min Range: -2.4810

Max Act: 2.2687. Min Act: -0.0000

Data Index: 479463 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 2.4810. Min Range: -2.4810

Max Act: 2.3745. Min Act: -0.0000

Data Index: 323452 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 2.4810. Min Range: -2.4810

Max Act: 2.3616. Min Act: -0.0000

Data Index: 518376 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 2.4810. Min Range: -2.4810

Max Act: 2.2964. Min Act: -0.0000

Data Index: 723787 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 2.4810. Min Range: -2.4810

Max Act: 2.0745. Min Act: -0.0000

Data Index: 1011489 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.8184. Min Act: -0.0000

Data Index: 1347910 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.8139. Min Act: -0.0000

Data Index: 1030027 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.7938. Min Act: -0.0000

Data Index: 517935 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.8337. Min Act: -0.0000

Data Index: 1329634 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.7115. Min Act: -0.0000

Data Index: 596556 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.8080. Min Act: -0.0000

Data Index: 440829 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.7731. Min Act: -0.0000

Data Index: 721522 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.7682. Min Act: -0.0000

Data Index: 412627 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.7578. Min Act: -0.0000

Data Index: 902627 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.7386. Min Act: -0.0000

Data Index: 970925 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.7230. Min Act: -0.0000

Data Index: 1113570 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.8017. Min Act: -0.0000

Data Index: 1242185 (C4 (Web Text))

Max Activating Token Index: 276