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

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

Neuron 4785 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1629135 (Python Code)

Max Activating Token Index: 758

Text #1

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0787. Min Act: -0.0000

Data Index: 1387745 (Python Code)

Max Activating Token Index: 305

Text #2

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1606007 (Python Code)

Max Activating Token Index: 358

Text #3

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1654152 (Python Code)

Max Activating Token Index: 593

Text #4

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1439246 (Python Code)

Max Activating Token Index: 93

Text #5

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1440460 (Python Code)

Max Activating Token Index: 905

Text #6

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1426911 (Python Code)

Max Activating Token Index: 577

Text #7

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1403285 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0628. Min Act: -0.0000

Data Index: 484678 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1476088 (Python Code)

Max Activating Token Index: 1022

Text #10

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1397241 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1456883 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0583. Min Act: -0.0000

Data Index: 1382057 (Python Code)

Max Activating Token Index: 1021

Text #13

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0561. Min Act: -0.0000

Data Index: 1643340 (Python Code)

Max Activating Token Index: 842

Text #14

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1182785 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0586. Min Act: -0.0000

Data Index: 841650 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1469036 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1371817 (Python Code)

Max Activating Token Index: 184

Text #18

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1446484 (Python Code)

Max Activating Token Index: 150

Text #19

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0530. Min Act: -0.0000

Data Index: 1543222 (Python Code)

Max Activating Token Index: 964