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

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

Neuron 958 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: 0.0653. Min Range: -0.0653

Max Act: 0.0653. Min Act: -0.0001

Data Index: 797874 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1023167 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0646. Min Act: -0.0001

Data Index: 545165 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0629. Min Act: -0.0001

Data Index: 792145 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0623. Min Act: -0.0001

Data Index: 929288 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0599. Min Act: -0.0001

Data Index: 252063 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1102369 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0584. Min Act: -0.0001

Data Index: 425179 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0560. Min Act: -0.0001

Data Index: 496117 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0560. Min Act: -0.0001

Data Index: 21068 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1105632 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0542. Min Act: -0.0001

Data Index: 52670 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0561. Min Act: -0.0001

Data Index: 398240 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0538. Min Act: -0.0001

Data Index: 549021 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1006733 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0562. Min Act: -0.0001

Data Index: 15214 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0533. Min Act: -0.0001

Data Index: 953108 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0536. Min Act: -0.0001

Data Index: 809609 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0515. Min Act: -0.0001

Data Index: 89593 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0507. Min Act: -0.0001

Data Index: 280995 (C4 (Web Text))

Max Activating Token Index: 51