Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 75 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.6578. Min Act: -0.0001

Data Index: 1138017 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5700. Min Act: -0.0001

Data Index: 418552 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.6419. Min Act: -0.0001

Data Index: 1031538 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.6100. Min Act: -0.0001

Data Index: 922805 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5857. Min Act: -0.0001

Data Index: 217243 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5849. Min Act: -0.0001

Data Index: 1098812 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5238. Min Act: -0.0001

Data Index: 774721 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5792. Min Act: -0.0001

Data Index: 717431 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.6515. Min Act: -0.0000

Data Index: 1359247 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5122. Min Act: -0.0001

Data Index: 1039293 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5802. Min Act: -0.0000

Data Index: 26181 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5805. Min Act: -0.0000

Data Index: 396938 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5329. Min Act: -0.0001

Data Index: 913577 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5737. Min Act: -0.0000

Data Index: 1033197 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5777. Min Act: -0.0001

Data Index: 227559 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.4699. Min Act: -0.0000

Data Index: 940042 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.5485. Min Act: -0.0001

Data Index: 886321 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.4820. Min Act: -0.0001

Data Index: 414184 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.6239. Min Act: -0.0001

Data Index: 142475 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.6578. Min Range: -1.6578

Max Act: 1.4442. Min Act: -0.0001

Data Index: 1234832 (C4 (Web Text))

Max Activating Token Index: 712