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

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

Neuron 382 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2459. Min Act: -0.0001

Data Index: 992427 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1237641 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1745. Min Act: -0.0001

Data Index: 667335 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1523. Min Act: -0.0001

Data Index: 816381 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1420. Min Act: -0.0001

Data Index: 325570 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1145271 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1107588 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1527. Min Act: -0.0001

Data Index: 397016 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1426. Min Act: -0.0001

Data Index: 666449 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1156045 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1370. Min Act: -0.0001

Data Index: 55550 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1363. Min Act: -0.0001

Data Index: 654331 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1302. Min Act: -0.0001

Data Index: 425836 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1331. Min Act: -0.0001

Data Index: 1087175 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1285. Min Act: -0.0001

Data Index: 360044 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1356283 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1319. Min Act: -0.0001

Data Index: 959220 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1276. Min Act: -0.0001

Data Index: 614371 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1340132 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1304. Min Act: -0.0001

Data Index: 1311179 (C4 (Web Text))

Max Activating Token Index: 442