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

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

Neuron 2855 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1834. Min Act: -0.0001

Data Index: 950299 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1203623 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1672. Min Act: -0.0001

Data Index: 650589 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1605. Min Act: -0.0001

Data Index: 7032 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1575. Min Act: -0.0001

Data Index: 195682 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1587. Min Act: -0.0001

Data Index: 431116 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1579. Min Act: -0.0001

Data Index: 995694 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1582. Min Act: -0.0001

Data Index: 319495 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1553. Min Act: -0.0001

Data Index: 120249 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1552. Min Act: -0.0001

Data Index: 930469 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1562. Min Act: -0.0001

Data Index: 884924 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1536. Min Act: -0.0001

Data Index: 470911 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1559. Min Act: -0.0001

Data Index: 478337 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1218273 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1533. Min Act: -0.0001

Data Index: 339393 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1192545 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1543. Min Act: -0.0001

Data Index: 317271 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1095922 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1453. Min Act: -0.0001

Data Index: 743788 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1470. Min Act: -0.0001

Data Index: 386797 (C4 (Web Text))

Max Activating Token Index: 156