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

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

Neuron 1662 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4960. Min Range: -2.4960

Max Act: 2.4960. Min Act: -0.0000

Data Index: 700919 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.7948. Min Act: -0.0000

Data Index: 1078364 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.9297. Min Act: -0.0000

Data Index: 280702 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.7790. Min Act: -0.0000

Data Index: 512017 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.7275. Min Act: -0.0000

Data Index: 217492 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.8433. Min Act: -0.0000

Data Index: 649911 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.6598. Min Act: -0.0000

Data Index: 1049085 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.6797. Min Act: -0.0000

Data Index: 224208 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.6473. Min Act: -0.0000

Data Index: 341075 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.7361. Min Act: -0.0000

Data Index: 172736 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.6837. Min Act: -0.0000

Data Index: 863964 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.7229. Min Act: -0.0000

Data Index: 1224625 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.7048. Min Act: -0.0000

Data Index: 1176979 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.7593. Min Act: -0.0000

Data Index: 1306896 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.7000. Min Act: -0.0000

Data Index: 1147005 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.7018. Min Act: -0.0000

Data Index: 1274643 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.7784. Min Act: -0.0000

Data Index: 1288557 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.5117. Min Act: -0.0000

Data Index: 221397 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.6851. Min Act: -0.0000

Data Index: 216243 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.5893. Min Act: -0.0000

Data Index: 777016 (C4 (Web Text))

Max Activating Token Index: 59