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

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

Neuron 2089 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: 0.9396. Min Range: -0.9396

Max Act: 0.9396. Min Act: -0.0000

Data Index: 990527 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.8783. Min Act: -0.0000

Data Index: 553030 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1398778 (Python Code)

Max Activating Token Index: 139

Text #3

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1562775 (Python Code)

Max Activating Token Index: 617

Text #4

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1221911 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1449022 (Python Code)

Max Activating Token Index: 578

Text #6

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.6864. Min Act: -0.0000

Data Index: 221858 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1278959 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1459207 (Python Code)

Max Activating Token Index: 238

Text #9

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.6896. Min Act: -0.0000

Data Index: 367449 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.6428. Min Act: -0.0000

Data Index: 507284 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.6156. Min Act: -0.0000

Data Index: 812062 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.6077. Min Act: -0.0000

Data Index: 534180 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.6511. Min Act: -0.0000

Data Index: 843910 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1012870 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1522283 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.6041. Min Act: -0.0000

Data Index: 972796 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.6430. Min Act: -0.0000

Data Index: 957355 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1579077 (Python Code)

Max Activating Token Index: 106

Text #19

Max Range: 0.9396. Min Range: -0.9396

Max Act: 0.5963. Min Act: -0.0000

Data Index: 180862 (C4 (Web Text))

Max Activating Token Index: 82