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

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

Neuron 128 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1153337 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.9550. Min Act: -0.0000

Data Index: 59265 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8788. Min Act: -0.0000

Data Index: 733466 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8448. Min Act: -0.0000

Data Index: 407779 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8421. Min Act: -0.0000

Data Index: 998370 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8748. Min Act: -0.0000

Data Index: 186078 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8506. Min Act: -0.0000

Data Index: 218686 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8245. Min Act: -0.0000

Data Index: 130178 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7853. Min Act: -0.0000

Data Index: 659121 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8021. Min Act: -0.0000

Data Index: 1166090 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8311. Min Act: -0.0000

Data Index: 70116 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7828. Min Act: -0.0000

Data Index: 138410 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7527. Min Act: -0.0000

Data Index: 560931 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7527. Min Act: -0.0000

Data Index: 571780 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7810. Min Act: -0.0000

Data Index: 911203 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6789. Min Act: -0.0000

Data Index: 64729 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7080. Min Act: -0.0000

Data Index: 863374 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7069. Min Act: -0.0000

Data Index: 460741 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7258. Min Act: -0.0000

Data Index: 395928 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6967. Min Act: -0.0000

Data Index: 606540 (C4 (Web Text))

Max Activating Token Index: 309