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

Dataset: The Pile

Neuron 1361 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1872147 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1559828 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1965292 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1419. Min Act: -0.0000

Data Index: 14934 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1493939 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1583151 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1036052 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1458. Min Act: -0.0000

Data Index: 837003 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1398. Min Act: -0.0000

Data Index: 906731 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1384. Min Act: -0.0000

Data Index: 12569 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1340. Min Act: -0.0000

Data Index: 701688 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1413. Min Act: -0.0000

Data Index: 1185531 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1716088 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1310. Min Act: -0.0000

Data Index: 659126 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1317. Min Act: 0.0000

Data Index: 497778 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1352. Min Act: -0.0000

Data Index: 1104001 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1348. Min Act: -0.0000

Data Index: 136463 (The Pile)

Max Activating Token Index: 81

Text #17

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1674578 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1197102 (The Pile)

Max Activating Token Index: 93

Text #19

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1701991 (The Pile)

Max Activating Token Index: 638