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

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

Neuron 4642 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.7553. Min Act: -0.0001

Data Index: 168292 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5683. Min Act: -0.0000

Data Index: 948266 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5395. Min Act: -0.0000

Data Index: 741573 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5212. Min Act: -0.0000

Data Index: 20493 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5389. Min Act: -0.0000

Data Index: 553746 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5143. Min Act: -0.0000

Data Index: 3480 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4631. Min Act: -0.0000

Data Index: 541015 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1280917 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4987. Min Act: -0.0000

Data Index: 123729 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1046034 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4592. Min Act: -0.0000

Data Index: 465587 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4747. Min Act: -0.0000

Data Index: 447527 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4593. Min Act: -0.0000

Data Index: 599893 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4630. Min Act: -0.0000

Data Index: 412145 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4897. Min Act: -0.0000

Data Index: 356981 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4853. Min Act: -0.0000

Data Index: 999109 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4838. Min Act: -0.0001

Data Index: 1261432 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4594. Min Act: -0.0000

Data Index: 584465 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1284213 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1040376 (C4 (Web Text))

Max Activating Token Index: 167