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

Dataset: The Pile

Neuron 2617 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1708966 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1424835 (The Pile)

Max Activating Token Index: 494

Text #2

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1535. Min Act: -0.0000

Data Index: 519154 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1367. Min Act: -0.0000

Data Index: 598930 (The Pile)

Max Activating Token Index: 895

Text #4

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1147480 (The Pile)

Max Activating Token Index: 136

Text #5

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1400. Min Act: -0.0000

Data Index: 1757745 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1293521 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1370. Min Act: -0.0000

Data Index: 698732 (The Pile)

Max Activating Token Index: 129

Text #8

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1471. Min Act: -0.0000

Data Index: 313622 (The Pile)

Max Activating Token Index: 898

Text #9

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1211439 (The Pile)

Max Activating Token Index: 352

Text #10

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1314. Min Act: -0.0000

Data Index: 146083 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1349. Min Act: -0.0000

Data Index: 119835 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1293. Min Act: -0.0000

Data Index: 528971 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1096906 (The Pile)

Max Activating Token Index: 330

Text #14

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1185. Min Act: -0.0000

Data Index: 802291 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1277. Min Act: -0.0000

Data Index: 618996 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1315328 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1294883 (The Pile)

Max Activating Token Index: 817

Text #18

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1301. Min Act: -0.0000

Data Index: 1418487 (The Pile)

Max Activating Token Index: 962

Text #19

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1253. Min Act: -0.0000

Data Index: 816555 (The Pile)

Max Activating Token Index: 182