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

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

Neuron 1438 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: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1318440 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0425. Min Act: -0.0000

Data Index: 1118855 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0408. Min Act: -0.0000

Data Index: 244079 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0388. Min Act: -0.0000

Data Index: 600618 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0360. Min Act: -0.0000

Data Index: 205527 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0379. Min Act: -0.0000

Data Index: 1284039 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0340. Min Act: -0.0000

Data Index: 497669 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0376. Min Act: -0.0000

Data Index: 975457 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0353. Min Act: -0.0000

Data Index: 589682 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1178837 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0331. Min Act: -0.0000

Data Index: 88863 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1127025 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0329. Min Act: -0.0000

Data Index: 975411 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0326. Min Act: -0.0000

Data Index: 731715 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0327. Min Act: -0.0000

Data Index: 629621 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1351881 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0329. Min Act: -0.0000

Data Index: 47228 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1121288 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0294. Min Act: -0.0000

Data Index: 688540 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0302. Min Act: -0.0000

Data Index: 106608 (C4 (Web Text))

Max Activating Token Index: 870