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

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

Neuron 1230 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5977. Min Range: -1.5977

Max Act: 1.5977. Min Act: -0.0001

Data Index: 1250047 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 1.5977. Min Range: -1.5977

Max Act: 1.3038. Min Act: -0.0001

Data Index: 748016 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 1.5977. Min Range: -1.5977

Max Act: 1.1347. Min Act: -0.0001

Data Index: 286962 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 1.5977. Min Range: -1.5977

Max Act: 1.1669. Min Act: -0.0001

Data Index: 882993 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 1.5977. Min Range: -1.5977

Max Act: 1.1185. Min Act: -0.0001

Data Index: 915894 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 1.5977. Min Range: -1.5977

Max Act: 1.1142. Min Act: -0.0001

Data Index: 344714 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.9613. Min Act: -0.0001

Data Index: 112824 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.5977. Min Range: -1.5977

Max Act: 1.0126. Min Act: -0.0001

Data Index: 692019 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 1.5977. Min Range: -1.5977

Max Act: 1.0218. Min Act: -0.0001

Data Index: 835501 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.9847. Min Act: -0.0001

Data Index: 1091166 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.9599. Min Act: -0.0001

Data Index: 608568 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.9437. Min Act: -0.0001

Data Index: 1322920 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.9764. Min Act: -0.0001

Data Index: 512409 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.9081. Min Act: -0.0001

Data Index: 1328126 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.9185. Min Act: -0.0001

Data Index: 1317586 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.9177. Min Act: -0.0001

Data Index: 704473 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.8891. Min Act: -0.0001

Data Index: 388777 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.9024. Min Act: -0.0001

Data Index: 935354 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.8674. Min Act: -0.0001

Data Index: 1403029 (Python Code)

Max Activating Token Index: 800

Text #19

Max Range: 1.5977. Min Range: -1.5977

Max Act: 0.9198. Min Act: -0.0001

Data Index: 1067986 (C4 (Web Text))

Max Activating Token Index: 940