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

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

Neuron 2690 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3917. Min Range: -2.3917

Max Act: 2.3917. Min Act: -0.0000

Data Index: 182192 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 2.3917. Min Range: -2.3917

Max Act: 2.0594. Min Act: -0.0000

Data Index: 1293166 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 2.3917. Min Range: -2.3917

Max Act: 2.0597. Min Act: -0.0000

Data Index: 781055 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.9569. Min Act: -0.0000

Data Index: 946517 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 2.3917. Min Range: -2.3917

Max Act: 2.0310. Min Act: -0.0000

Data Index: 460666 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.9177. Min Act: -0.0000

Data Index: 132514 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.9137. Min Act: -0.0000

Data Index: 818911 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.8895. Min Act: -0.0000

Data Index: 1234717 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.8666. Min Act: -0.0000

Data Index: 97601 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.7674. Min Act: -0.0000

Data Index: 849902 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.7059. Min Act: -0.0000

Data Index: 1630012 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.9002. Min Act: -0.0000

Data Index: 96241 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.7156. Min Act: -0.0000

Data Index: 495697 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.7896. Min Act: -0.0000

Data Index: 972797 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.7353. Min Act: -0.0000

Data Index: 1133488 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.6957. Min Act: -0.0000

Data Index: 678265 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.6484. Min Act: -0.0000

Data Index: 305771 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.7321. Min Act: -0.0000

Data Index: 850151 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.7279. Min Act: -0.0000

Data Index: 858990 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 2.3917. Min Range: -2.3917

Max Act: 1.7159. Min Act: -0.0000

Data Index: 1349291 (C4 (Web Text))

Max Activating Token Index: 126