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

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

Neuron 2887 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1462261 (Python Code)

Max Activating Token Index: 370

Text #1

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1412413 (Python Code)

Max Activating Token Index: 553

Text #2

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1567. Min Act: -0.0000

Data Index: 275816 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1433174 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1365790 (Python Code)

Max Activating Token Index: 730

Text #5

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1573219 (Python Code)

Max Activating Token Index: 424

Text #6

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1333547 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1285248 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1633229 (Python Code)

Max Activating Token Index: 510

Text #9

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1397211 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1223. Min Act: -0.0000

Data Index: 1516778 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1044. Min Act: -0.0000

Data Index: 827451 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1608778 (Python Code)

Max Activating Token Index: 1012

Text #13

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1506095 (Python Code)

Max Activating Token Index: 851

Text #14

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1244. Min Act: -0.0000

Data Index: 31358 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1646589 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1635033 (Python Code)

Max Activating Token Index: 825

Text #17

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1084094 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1145. Min Act: -0.0000

Data Index: 768683 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1564432 (Python Code)

Max Activating Token Index: 372