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

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

Neuron 3295 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9402. Min Act: -0.0000

Data Index: 734455 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7977. Min Act: -0.0000

Data Index: 892331 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7813. Min Act: -0.0000

Data Index: 167395 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7501. Min Act: -0.0000

Data Index: 393194 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7988. Min Act: -0.0000

Data Index: 72025 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6846. Min Act: -0.0000

Data Index: 754891 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7842. Min Act: -0.0000

Data Index: 889110 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6546. Min Act: -0.0000

Data Index: 660313 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6964. Min Act: -0.0000

Data Index: 968672 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1299625 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6790. Min Act: -0.0000

Data Index: 863508 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7229. Min Act: -0.0000

Data Index: 1300335 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6627. Min Act: -0.0000

Data Index: 330483 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6434. Min Act: -0.0000

Data Index: 476181 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6412. Min Act: -0.0000

Data Index: 966429 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6203. Min Act: -0.0000

Data Index: 422541 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6478. Min Act: -0.0000

Data Index: 627114 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6142. Min Act: -0.0000

Data Index: 983147 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1110013 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1209436 (C4 (Web Text))

Max Activating Token Index: 301