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

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

Neuron 4704 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0653. Min Act: -0.0001

Data Index: 399901 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1259309 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0581. Min Act: -0.0000

Data Index: 264056 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0634. Min Act: -0.0001

Data Index: 403447 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0572. Min Act: -0.0001

Data Index: 1032384 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1081380 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0532. Min Act: -0.0000

Data Index: 1038352 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0494. Min Act: -0.0000

Data Index: 669910 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0516. Min Act: -0.0000

Data Index: 84508 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0509. Min Act: -0.0000

Data Index: 254655 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0540. Min Act: -0.0001

Data Index: 741223 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0515. Min Act: -0.0001

Data Index: 1230210 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0460. Min Act: -0.0000

Data Index: 98824 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1141048 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0499. Min Act: -0.0000

Data Index: 996075 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0473. Min Act: -0.0001

Data Index: 940172 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0487. Min Act: -0.0001

Data Index: 975327 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1166910 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1243638 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0489. Min Act: -0.0001

Data Index: 159844 (C4 (Web Text))

Max Activating Token Index: 30