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

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

Neuron 401 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7415. Min Range: -2.7415

Max Act: 2.7415. Min Act: -0.0000

Data Index: 657727 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 2.7415. Min Range: -2.7415

Max Act: 2.6809. Min Act: -0.0000

Data Index: 1643920 (Python Code)

Max Activating Token Index: 448

Text #2

Max Range: 2.7415. Min Range: -2.7415

Max Act: 2.0898. Min Act: -0.0000

Data Index: 325855 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 2.7415. Min Range: -2.7415

Max Act: 2.2835. Min Act: -0.0000

Data Index: 508943 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 2.7415. Min Range: -2.7415

Max Act: 2.1271. Min Act: -0.0000

Data Index: 940103 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 2.7415. Min Range: -2.7415

Max Act: 2.0263. Min Act: -0.0000

Data Index: 778551 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 2.7415. Min Range: -2.7415

Max Act: 2.0315. Min Act: -0.0000

Data Index: 1562587 (Python Code)

Max Activating Token Index: 178

Text #7

Max Range: 2.7415. Min Range: -2.7415

Max Act: 2.0160. Min Act: -0.0000

Data Index: 414983 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.9475. Min Act: -0.0000

Data Index: 1452253 (Python Code)

Max Activating Token Index: 413

Text #9

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.9263. Min Act: -0.0000

Data Index: 269473 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.8410. Min Act: -0.0000

Data Index: 1495597 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.8380. Min Act: -0.0000

Data Index: 1475178 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.8358. Min Act: -0.0000

Data Index: 5887 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.6972. Min Act: -0.0000

Data Index: 801342 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.7886. Min Act: -0.0000

Data Index: 1637730 (Python Code)

Max Activating Token Index: 543

Text #15

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.7773. Min Act: -0.0000

Data Index: 119299 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.5483. Min Act: -0.0000

Data Index: 965471 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.8442. Min Act: -0.0000

Data Index: 1643841 (Python Code)

Max Activating Token Index: 108

Text #18

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.7480. Min Act: -0.0000

Data Index: 1525428 (Python Code)

Max Activating Token Index: 335

Text #19

Max Range: 2.7415. Min Range: -2.7415

Max Act: 1.7384. Min Act: -0.0000

Data Index: 1438509 (Python Code)

Max Activating Token Index: 388