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

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

Neuron 3325 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.8383. Min Act: -0.0000

Data Index: 666877 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.8110. Min Act: -0.0000

Data Index: 326360 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.7341. Min Act: -0.0000

Data Index: 707121 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.6803. Min Act: -0.0000

Data Index: 279536 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.7762. Min Act: -0.0000

Data Index: 508220 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1161894 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1005247 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1104762 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.6086. Min Act: -0.0000

Data Index: 337980 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1030567 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1135659 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1199891 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5440. Min Act: -0.0000

Data Index: 3956 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5231. Min Act: -0.0000

Data Index: 67020 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5352. Min Act: -0.0000

Data Index: 362004 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5464. Min Act: -0.0000

Data Index: 913393 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.4939. Min Act: -0.0000

Data Index: 930454 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5178. Min Act: -0.0000

Data Index: 164670 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1139991 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.4646. Min Act: -0.0000

Data Index: 813703 (C4 (Web Text))

Max Activating Token Index: 797