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

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

Neuron 3289 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0003

Data Index: 1430460 (Python Code)

Max Activating Token Index: 489

Text #1

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1432. Min Act: -0.0003

Data Index: 1565425 (Python Code)

Max Activating Token Index: 513

Text #2

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1414. Min Act: -0.0003

Data Index: 1484049 (Python Code)

Max Activating Token Index: 512

Text #3

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1366. Min Act: -0.0003

Data Index: 1591684 (Python Code)

Max Activating Token Index: 611

Text #4

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1337. Min Act: -0.0003

Data Index: 1627206 (Python Code)

Max Activating Token Index: 718

Text #5

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1427. Min Act: -0.0003

Data Index: 1629577 (Python Code)

Max Activating Token Index: 445

Text #6

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1358. Min Act: -0.0003

Data Index: 1594766 (Python Code)

Max Activating Token Index: 480

Text #7

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1407. Min Act: -0.0003

Data Index: 1416183 (Python Code)

Max Activating Token Index: 340

Text #8

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1305. Min Act: -0.0003

Data Index: 1435513 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1293. Min Act: -0.0003

Data Index: 1524988 (Python Code)

Max Activating Token Index: 348

Text #10

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1296. Min Act: -0.0003

Data Index: 1414084 (Python Code)

Max Activating Token Index: 569

Text #11

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1230. Min Act: -0.0003

Data Index: 1586225 (Python Code)

Max Activating Token Index: 527

Text #12

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1281. Min Act: -0.0003

Data Index: 1362918 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1275. Min Act: -0.0003

Data Index: 1501834 (Python Code)

Max Activating Token Index: 404

Text #14

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1193. Min Act: -0.0003

Data Index: 1514827 (Python Code)

Max Activating Token Index: 512

Text #15

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1293. Min Act: -0.0003

Data Index: 1531395 (Python Code)

Max Activating Token Index: 568

Text #16

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1266. Min Act: -0.0003

Data Index: 1518954 (Python Code)

Max Activating Token Index: 457

Text #17

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1307. Min Act: -0.0003

Data Index: 1454245 (Python Code)

Max Activating Token Index: 330

Text #18

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1252. Min Act: -0.0003

Data Index: 1500318 (Python Code)

Max Activating Token Index: 430

Text #19

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1306. Min Act: -0.0003

Data Index: 1569830 (Python Code)

Max Activating Token Index: 425