Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 589 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1551921 (Python Code)

Max Activating Token Index: 867

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0428. Min Act: -0.0000

Data Index: 1181025 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0477. Min Act: -0.0000

Data Index: 788052 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1054208 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0382. Min Act: -0.0000

Data Index: 1487889 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1514317 (Python Code)

Max Activating Token Index: 453

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1648952 (Python Code)

Max Activating Token Index: 854

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1145419 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0361. Min Act: -0.0001

Data Index: 723825 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0370. Min Act: -0.0000

Data Index: 694834 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1032252 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0305. Min Act: -0.0001

Data Index: 639346 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0365. Min Act: -0.0000

Data Index: 1537548 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0357. Min Act: -0.0001

Data Index: 21048 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1161428 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0351. Min Act: -0.0000

Data Index: 132935 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1344065 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1486302 (Python Code)

Max Activating Token Index: 225

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0371. Min Act: -0.0001

Data Index: 304176 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0361. Min Act: -0.0001

Data Index: 710332 (C4 (Web Text))

Max Activating Token Index: 317