Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 894 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0945. Min Act: -0.0003

Data Index: 1478212 (Python Code)

Max Activating Token Index: 414

Text #1

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0903. Min Act: -0.0003

Data Index: 1419578 (Python Code)

Max Activating Token Index: 932

Text #2

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0808. Min Act: -0.0003

Data Index: 1578829 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0682. Min Act: -0.0003

Data Index: 1636550 (Python Code)

Max Activating Token Index: 862

Text #4

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1480194 (Python Code)

Max Activating Token Index: 874

Text #5

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1543997 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0624. Min Act: -0.0003

Data Index: 1600524 (Python Code)

Max Activating Token Index: 680

Text #7

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1449822 (Python Code)

Max Activating Token Index: 281

Text #8

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0614. Min Act: -0.0003

Data Index: 1561047 (Python Code)

Max Activating Token Index: 202

Text #9

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0577. Min Act: -0.0003

Data Index: 1522310 (Python Code)

Max Activating Token Index: 797

Text #10

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1424503 (Python Code)

Max Activating Token Index: 159

Text #11

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1381101 (Python Code)

Max Activating Token Index: 46

Text #12

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1505910 (Python Code)

Max Activating Token Index: 851

Text #13

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1360471 (Python Code)

Max Activating Token Index: 1017

Text #14

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1606736 (Python Code)

Max Activating Token Index: 71

Text #15

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1555887 (Python Code)

Max Activating Token Index: 262

Text #16

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1471176 (Python Code)

Max Activating Token Index: 885

Text #17

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1587648 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1399522 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1368161 (Python Code)

Max Activating Token Index: 168