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

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

Neuron 648 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8666. Min Act: -0.0000

Data Index: 984252 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.6821. Min Act: 0.0000

Data Index: 1009085 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1029114 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1019427 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.8719. Min Act: -0.0000

Data Index: 143963 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.7840. Min Act: -0.0000

Data Index: 741428 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1182499 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.8292. Min Act: -0.0000

Data Index: 815019 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.7809. Min Act: -0.0000

Data Index: 515010 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1340654 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.8190. Min Act: -0.0000

Data Index: 340970 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.7277. Min Act: -0.0000

Data Index: 647329 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.7347. Min Act: -0.0000

Data Index: 311682 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.7145. Min Act: -0.0000

Data Index: 294113 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1169236 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.6467. Min Act: -0.0000

Data Index: 53760 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1080206 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.5808. Min Act: -0.0000

Data Index: 412559 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1647831 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 1.8666. Min Range: -1.8666

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1102103 (C4 (Web Text))

Max Activating Token Index: 632