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

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

Neuron 3829 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1361995 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7345. Min Act: -0.0001

Data Index: 1603449 (Python Code)

Max Activating Token Index: 189

Text #2

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6622. Min Act: -0.0001

Data Index: 1551148 (Python Code)

Max Activating Token Index: 815

Text #3

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7015. Min Act: -0.0001

Data Index: 1415508 (Python Code)

Max Activating Token Index: 218

Text #4

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6369. Min Act: -0.0001

Data Index: 1482163 (Python Code)

Max Activating Token Index: 996

Text #5

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1553442 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6234. Min Act: -0.0001

Data Index: 1531770 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5868. Min Act: -0.0001

Data Index: 1431975 (Python Code)

Max Activating Token Index: 127

Text #8

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5975. Min Act: -0.0001

Data Index: 1631740 (Python Code)

Max Activating Token Index: 837

Text #9

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1653321 (Python Code)

Max Activating Token Index: 405

Text #10

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5505. Min Act: -0.0001

Data Index: 1456676 (Python Code)

Max Activating Token Index: 188

Text #11

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5692. Min Act: -0.0001

Data Index: 1626031 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6177. Min Act: -0.0001

Data Index: 1628829 (Python Code)

Max Activating Token Index: 892

Text #13

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5500. Min Act: -0.0001

Data Index: 1629121 (Python Code)

Max Activating Token Index: 380

Text #14

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5668. Min Act: -0.0001

Data Index: 1609614 (Python Code)

Max Activating Token Index: 625

Text #15

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1399465 (Python Code)

Max Activating Token Index: 954

Text #16

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5436. Min Act: -0.0001

Data Index: 1599331 (Python Code)

Max Activating Token Index: 1019

Text #17

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5585. Min Act: -0.0001

Data Index: 1525242 (Python Code)

Max Activating Token Index: 406

Text #18

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6042. Min Act: -0.0001

Data Index: 1596071 (Python Code)

Max Activating Token Index: 959

Text #19

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5385. Min Act: -0.0001

Data Index: 1607938 (Python Code)

Max Activating Token Index: 94