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

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

Neuron 4542 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: 2.0677. Min Range: -2.0677

Max Act: 2.0677. Min Act: -0.0000

Data Index: 1387759 (Python Code)

Max Activating Token Index: 985

Text #1

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.9198. Min Act: -0.0000

Data Index: 919319 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.8253. Min Act: -0.0000

Data Index: 1019041 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.8169. Min Act: -0.0000

Data Index: 286614 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 2.0677. Min Range: -2.0677

Max Act: 2.0407. Min Act: -0.0000

Data Index: 579305 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6505. Min Act: -0.0000

Data Index: 260265 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6441. Min Act: -0.0000

Data Index: 1237446 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6650. Min Act: -0.0000

Data Index: 639837 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.7354. Min Act: -0.0000

Data Index: 453567 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.5831. Min Act: -0.0000

Data Index: 615460 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6119. Min Act: -0.0000

Data Index: 1018623 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.8832. Min Act: -0.0000

Data Index: 1228687 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6743. Min Act: -0.0000

Data Index: 622048 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6350. Min Act: -0.0000

Data Index: 1276966 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6512. Min Act: -0.0000

Data Index: 1056108 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6038. Min Act: -0.0000

Data Index: 1255095 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.5978. Min Act: -0.0000

Data Index: 104540 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.5695. Min Act: -0.0000

Data Index: 1430116 (Python Code)

Max Activating Token Index: 674

Text #18

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.5368. Min Act: -0.0000

Data Index: 272817 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6461. Min Act: -0.0000

Data Index: 198031 (C4 (Web Text))

Max Activating Token Index: 127