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

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

Neuron 751 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0201. Min Range: -1.0201

Max Act: 1.0201. Min Act: -0.0000

Data Index: 43475 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9531. Min Act: -0.0000

Data Index: 511708 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.7088. Min Act: -0.0000

Data Index: 44630 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.7541. Min Act: -0.0000

Data Index: 746905 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1093126 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.6315. Min Act: 0.0000

Data Index: 196421 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.6595. Min Act: 0.0000

Data Index: 550064 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.6287. Min Act: -0.0000

Data Index: 252499 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.6341. Min Act: -0.0000

Data Index: 781483 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.6223. Min Act: 0.0000

Data Index: 768274 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1362587 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.6089. Min Act: -0.0000

Data Index: 727659 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1634151 (Python Code)

Max Activating Token Index: 174

Text #13

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.5535. Min Act: -0.0000

Data Index: 92624 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.5874. Min Act: 0.0000

Data Index: 125806 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.5843. Min Act: -0.0000

Data Index: 971372 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.5726. Min Act: -0.0000

Data Index: 445223 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.5479. Min Act: 0.0000

Data Index: 1363123 (Python Code)

Max Activating Token Index: 756

Text #18

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.5610. Min Act: 0.0000

Data Index: 437551 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.5569. Min Act: 0.0000

Data Index: 491685 (C4 (Web Text))

Max Activating Token Index: 628