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

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

Neuron 3645 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: 0.7752. Min Range: -0.7752

Max Act: 0.7752. Min Act: -0.0000

Data Index: 888439 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1380008 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.7051. Min Act: -0.0000

Data Index: 204137 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1590625 (Python Code)

Max Activating Token Index: 178

Text #4

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1149537 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1426086 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1491090 (Python Code)

Max Activating Token Index: 502

Text #7

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1617716 (Python Code)

Max Activating Token Index: 747

Text #8

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.6243. Min Act: -0.0000

Data Index: 14622 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1603720 (Python Code)

Max Activating Token Index: 671

Text #10

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1603265 (Python Code)

Max Activating Token Index: 159

Text #11

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1424310 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1141019 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1640645 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.5514. Min Act: -0.0000

Data Index: 224545 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1520917 (Python Code)

Max Activating Token Index: 383

Text #16

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1414094 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1458107 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1417083 (Python Code)

Max Activating Token Index: 753

Text #19

Max Range: 0.7752. Min Range: -0.7752

Max Act: 0.5445. Min Act: -0.0000

Data Index: 697106 (C4 (Web Text))

Max Activating Token Index: 38