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

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

Neuron 1105 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1816. Min Act: -0.0001

Data Index: 301523 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1724. Min Act: -0.0001

Data Index: 1350185 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1607. Min Act: -0.0001

Data Index: 639392 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1509. Min Act: -0.0001

Data Index: 943881 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1550. Min Act: -0.0001

Data Index: 75126 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1536. Min Act: -0.0001

Data Index: 926862 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1550. Min Act: -0.0001

Data Index: 42183 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1480. Min Act: -0.0001

Data Index: 437513 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1467. Min Act: -0.0001

Data Index: 554541 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1462. Min Act: -0.0001

Data Index: 846371 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1506. Min Act: -0.0001

Data Index: 955619 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1311174 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1365. Min Act: -0.0001

Data Index: 430070 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1413. Min Act: -0.0000

Data Index: 1292064 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1375. Min Act: -0.0001

Data Index: 59262 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1394. Min Act: -0.0000

Data Index: 469480 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1319. Min Act: -0.0001

Data Index: 937931 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1198377 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1366. Min Act: -0.0001

Data Index: 678919 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1347. Min Act: -0.0001

Data Index: 902573 (C4 (Web Text))

Max Activating Token Index: 859