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

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

Neuron 4800 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.7543. Min Act: -0.0000

Data Index: 372337 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1301099 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1305334 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5369. Min Act: -0.0000

Data Index: 854521 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5281. Min Act: -0.0000

Data Index: 143366 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5041. Min Act: -0.0000

Data Index: 559804 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5015. Min Act: -0.0000

Data Index: 172054 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4997. Min Act: -0.0000

Data Index: 94183 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1204224 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4836. Min Act: -0.0000

Data Index: 66894 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4748. Min Act: 0.0000

Data Index: 11905 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4493. Min Act: -0.0000

Data Index: 599312 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4514. Min Act: -0.0000

Data Index: 796917 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1060498 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1349502 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1044041 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4559. Min Act: -0.0000

Data Index: 533561 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4227. Min Act: -0.0000

Data Index: 233698 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4356. Min Act: -0.0000

Data Index: 565946 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.4445. Min Act: -0.0000

Data Index: 526956 (C4 (Web Text))

Max Activating Token Index: 322