Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2515 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1503785 (Python Code)

Max Activating Token Index: 1002

Text #1

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1469059 (Python Code)

Max Activating Token Index: 1014

Text #2

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1523606 (Python Code)

Max Activating Token Index: 990

Text #3

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1507772 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1627046 (Python Code)

Max Activating Token Index: 1017

Text #5

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1525551 (Python Code)

Max Activating Token Index: 1001

Text #6

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1359948 (Python Code)

Max Activating Token Index: 1015

Text #7

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1440185 (Python Code)

Max Activating Token Index: 1005

Text #8

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1571084 (Python Code)

Max Activating Token Index: 1011

Text #9

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1400902 (Python Code)

Max Activating Token Index: 1012

Text #10

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1527152 (Python Code)

Max Activating Token Index: 963

Text #11

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1378450 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1385759 (Python Code)

Max Activating Token Index: 1019

Text #13

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1498424 (Python Code)

Max Activating Token Index: 1022

Text #14

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1549469 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1502505 (Python Code)

Max Activating Token Index: 999

Text #16

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1490652 (Python Code)

Max Activating Token Index: 1020

Text #17

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1632361 (Python Code)

Max Activating Token Index: 1001

Text #18

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1602585 (Python Code)

Max Activating Token Index: 981

Text #19

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1582503 (Python Code)

Max Activating Token Index: 1019