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

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

Neuron 1427 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.7493. Min Act: -0.0000

Data Index: 433980 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.6783. Min Act: -0.0000

Data Index: 427263 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.6722. Min Act: -0.0000

Data Index: 308350 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.6685. Min Act: -0.0000

Data Index: 307002 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1271505 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5595. Min Act: -0.0000

Data Index: 887751 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5851. Min Act: -0.0000

Data Index: 238394 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5422. Min Act: -0.0000

Data Index: 849549 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5205. Min Act: -0.0000

Data Index: 392413 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5333. Min Act: -0.0000

Data Index: 591389 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5326. Min Act: -0.0000

Data Index: 106650 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1186403 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5518. Min Act: -0.0000

Data Index: 974037 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5501. Min Act: -0.0000

Data Index: 123410 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5247. Min Act: -0.0000

Data Index: 455850 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.4887. Min Act: -0.0000

Data Index: 507464 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5644. Min Act: -0.0000

Data Index: 745355 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1245685 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5355. Min Act: -0.0000

Data Index: 326211 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.7493. Min Range: -0.7493

Max Act: 0.5492. Min Act: -0.0000

Data Index: 391745 (C4 (Web Text))

Max Activating Token Index: 639