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

Dataset: The Pile

Neuron 3008 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.3579. Min Act: -0.0000

Data Index: 1802501 (The Pile)

Max Activating Token Index: 981

Text #1

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.3921. Min Act: -0.0000

Data Index: 1773343 (The Pile)

Max Activating Token Index: 556

Text #2

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1213741 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.2449. Min Act: -0.0000

Data Index: 589624 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.2128. Min Act: -0.0000

Data Index: 480949 (The Pile)

Max Activating Token Index: 329

Text #5

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1754. Min Act: -0.0000

Data Index: 1029503 (The Pile)

Max Activating Token Index: 42

Text #6

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1589963 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1403. Min Act: -0.0000

Data Index: 1476324 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1334. Min Act: -0.0000

Data Index: 1153035 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1702. Min Act: -0.0000

Data Index: 1339446 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1598. Min Act: -0.0000

Data Index: 573136 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1575. Min Act: -0.0000

Data Index: 236354 (The Pile)

Max Activating Token Index: 45

Text #12

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.0855. Min Act: -0.0001

Data Index: 930148 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1123577 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1171309 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1367. Min Act: -0.0000

Data Index: 1433743 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1487116 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1385. Min Act: -0.0000

Data Index: 208440 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1264341 (The Pile)

Max Activating Token Index: 455

Text #19

Max Range: 1.3921. Min Range: -1.3921

Max Act: 1.1686. Min Act: -0.0000

Data Index: 724548 (The Pile)

Max Activating Token Index: 946