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

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

Neuron 1567 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: 1.2768. Min Range: -1.2768

Max Act: 1.2768. Min Act: -0.0000

Data Index: 1157034 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1144539 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0377. Min Act: -0.0000

Data Index: 235532 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0440. Min Act: -0.0000

Data Index: 737755 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0331. Min Act: -0.0000

Data Index: 208419 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0365. Min Act: -0.0000

Data Index: 864347 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1229408 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1280526 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0092. Min Act: -0.0000

Data Index: 166479 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9497. Min Act: -0.0000

Data Index: 517074 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9973. Min Act: -0.0000

Data Index: 700840 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9878. Min Act: -0.0000

Data Index: 489705 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9800. Min Act: -0.0000

Data Index: 773517 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9607. Min Act: -0.0000

Data Index: 708666 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9588. Min Act: -0.0000

Data Index: 551783 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1240078 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1050447 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1132658 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9345. Min Act: -0.0000

Data Index: 297136 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9229. Min Act: -0.0000

Data Index: 565170 (C4 (Web Text))

Max Activating Token Index: 138