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

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

Neuron 157 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3454. Min Range: -2.3454

Max Act: 2.3454. Min Act: -0.0000

Data Index: 940883 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.9923. Min Act: -0.0000

Data Index: 353918 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 2.3454. Min Range: -2.3454

Max Act: 2.0820. Min Act: -0.0000

Data Index: 894987 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 2.3454. Min Range: -2.3454

Max Act: 2.0401. Min Act: -0.0000

Data Index: 719472 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.9904. Min Act: -0.0000

Data Index: 395510 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.9877. Min Act: -0.0000

Data Index: 587306 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.9600. Min Act: -0.0000

Data Index: 467480 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.8968. Min Act: -0.0000

Data Index: 768690 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.8320. Min Act: -0.0000

Data Index: 853601 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.7187. Min Act: -0.0000

Data Index: 687835 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.8049. Min Act: -0.0000

Data Index: 1123284 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.7683. Min Act: -0.0000

Data Index: 315751 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.7675. Min Act: -0.0000

Data Index: 1140916 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.7699. Min Act: -0.0000

Data Index: 652213 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.7047. Min Act: -0.0000

Data Index: 399959 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.6290. Min Act: -0.0000

Data Index: 942480 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.5254. Min Act: -0.0000

Data Index: 309424 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.6835. Min Act: -0.0000

Data Index: 1331934 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.5961. Min Act: -0.0000

Data Index: 596587 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 2.3454. Min Range: -2.3454

Max Act: 1.6814. Min Act: -0.0000

Data Index: 929423 (C4 (Web Text))

Max Activating Token Index: 964