Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 945 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.9050. Min Act: -0.0000

Data Index: 998555 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8853. Min Act: -0.0000

Data Index: 155555 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1416331 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1320723 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8215. Min Act: -0.0000

Data Index: 290343 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8236. Min Act: -0.0000

Data Index: 316903 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1466322 (Python Code)

Max Activating Token Index: 382

Text #7

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8327. Min Act: -0.0000

Data Index: 129423 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1158802 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7924. Min Act: -0.0000

Data Index: 812613 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1652614 (Python Code)

Max Activating Token Index: 778

Text #11

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1339600 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8082. Min Act: -0.0000

Data Index: 248547 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7943. Min Act: -0.0000

Data Index: 1475169 (Python Code)

Max Activating Token Index: 707

Text #14

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7885. Min Act: -0.0000

Data Index: 403411 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8221. Min Act: -0.0001

Data Index: 1399978 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7842. Min Act: -0.0000

Data Index: 379225 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1439345 (Python Code)

Max Activating Token Index: 596

Text #18

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8535. Min Act: -0.0000

Data Index: 350966 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7924. Min Act: -0.0000

Data Index: 429232 (C4 (Web Text))

Max Activating Token Index: 209