Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2135 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.2368. Min Act: -0.0000

Data Index: 170619 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.3340. Min Act: -0.0000

Data Index: 687039 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1531216 (Python Code)

Max Activating Token Index: 274

Text #3

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1310321 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.0484. Min Act: -0.0000

Data Index: 346818 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.0528. Min Act: -0.0000

Data Index: 430862 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.0951. Min Act: -0.0000

Data Index: 485756 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.0722. Min Act: -0.0000

Data Index: 241606 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1251. Min Act: -0.0000

Data Index: 1471384 (Python Code)

Max Activating Token Index: 787

Text #9

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1450926 (Python Code)

Max Activating Token Index: 581

Text #10

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.0351. Min Act: -0.0000

Data Index: 66805 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 1.3340. Min Range: -1.3340

Max Act: 0.9995. Min Act: -0.0000

Data Index: 676081 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 1.3340. Min Range: -1.3340

Max Act: 0.9328. Min Act: -0.0000

Data Index: 940613 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 1.3340. Min Range: -1.3340

Max Act: 0.9215. Min Act: -0.0000

Data Index: 826544 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 1.3340. Min Range: -1.3340

Max Act: 0.8369. Min Act: -0.0000

Data Index: 655251 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 1.3340. Min Range: -1.3340

Max Act: 0.9033. Min Act: -0.0000

Data Index: 1236105 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 1.3340. Min Range: -1.3340

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1111974 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 1.3340. Min Range: -1.3340

Max Act: 0.8229. Min Act: -0.0000

Data Index: 876790 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 1.3340. Min Range: -1.3340

Max Act: 0.8725. Min Act: -0.0000

Data Index: 63395 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 1.3340. Min Range: -1.3340

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1471554 (Python Code)

Max Activating Token Index: 306