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

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

Neuron 2606 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1080610 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1884. Min Act: -0.0001

Data Index: 131024 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1595. Min Act: -0.0001

Data Index: 111781 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1695. Min Act: -0.0001

Data Index: 793129 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1485. Min Act: -0.0001

Data Index: 20345 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1640. Min Act: -0.0001

Data Index: 875811 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1142113 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1459. Min Act: -0.0001

Data Index: 757852 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1426. Min Act: -0.0001

Data Index: 675368 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1362. Min Act: -0.0001

Data Index: 463717 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1000093 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1414. Min Act: -0.0001

Data Index: 450145 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1373. Min Act: -0.0001

Data Index: 94495 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1345033 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1398. Min Act: -0.0001

Data Index: 126037 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1500. Min Act: -0.0001

Data Index: 356614 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1250501 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1289526 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1387. Min Act: -0.0001

Data Index: 755644 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1337. Min Act: -0.0001

Data Index: 734269 (C4 (Web Text))

Max Activating Token Index: 366