Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 407 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1527. Min Act: -0.0001

Data Index: 403760 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1568. Min Act: -0.0001

Data Index: 361556 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1484. Min Act: -0.0001

Data Index: 977431 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1445. Min Act: -0.0001

Data Index: 457329 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1516. Min Act: -0.0001

Data Index: 214978 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1384. Min Act: -0.0001

Data Index: 532495 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1390. Min Act: -0.0001

Data Index: 575352 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1338. Min Act: -0.0001

Data Index: 569119 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1328. Min Act: -0.0001

Data Index: 99092 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1427. Min Act: -0.0001

Data Index: 993636 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1316. Min Act: -0.0001

Data Index: 393708 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1211. Min Act: -0.0001

Data Index: 184549 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1367. Min Act: -0.0001

Data Index: 423748 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1306. Min Act: -0.0001

Data Index: 480757 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1362. Min Act: -0.0001

Data Index: 338663 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1286. Min Act: -0.0001

Data Index: 906106 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1352. Min Act: -0.0001

Data Index: 594700 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1351164 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1274. Min Act: -0.0001

Data Index: 466485 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1254. Min Act: -0.0001

Data Index: 833161 (C4 (Web Text))

Max Activating Token Index: 682