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

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

Neuron 953 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: 0.5571. Min Range: -0.5571

Max Act: 0.5571. Min Act: -0.0000

Data Index: 42833 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4605. Min Act: 0.0001

Data Index: 633963 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4420. Min Act: -0.0000

Data Index: 73069 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4556. Min Act: -0.0000

Data Index: 568862 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4102. Min Act: -0.0000

Data Index: 272191 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4179. Min Act: -0.0000

Data Index: 219968 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3638. Min Act: -0.0000

Data Index: 129611 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3542. Min Act: -0.0000

Data Index: 261725 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1227601 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1298729 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3183. Min Act: 0.0000

Data Index: 599344 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3379. Min Act: -0.0000

Data Index: 20509 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3244. Min Act: -0.0000

Data Index: 509134 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3251. Min Act: -0.0000

Data Index: 642044 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3252. Min Act: -0.0000

Data Index: 113814 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3195. Min Act: -0.0000

Data Index: 660999 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1298921 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3183. Min Act: -0.0000

Data Index: 418216 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3126. Min Act: -0.0000

Data Index: 392551 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3274. Min Act: -0.0000

Data Index: 774981 (C4 (Web Text))

Max Activating Token Index: 831