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

Dataset: The Pile

Neuron 3780 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.5406. Min Act: -0.0000

Data Index: 1553521 (The Pile)

Max Activating Token Index: 447

Text #1

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.5202. Min Act: -0.0000

Data Index: 110715 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.3499. Min Act: -0.0000

Data Index: 430017 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.4467. Min Act: -0.0000

Data Index: 1549536 (The Pile)

Max Activating Token Index: 654

Text #4

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.3982. Min Act: -0.0000

Data Index: 876190 (The Pile)

Max Activating Token Index: 550

Text #5

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.3953. Min Act: -0.0000

Data Index: 1198473 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1293195 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.3893. Min Act: -0.0000

Data Index: 666923 (The Pile)

Max Activating Token Index: 921

Text #8

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1913125 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.3694. Min Act: -0.0000

Data Index: 856037 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1056199 (The Pile)

Max Activating Token Index: 698

Text #11

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.3325. Min Act: -0.0000

Data Index: 929534 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.2695. Min Act: -0.0000

Data Index: 692786 (The Pile)

Max Activating Token Index: 715

Text #13

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.2212. Min Act: -0.0000

Data Index: 353946 (The Pile)

Max Activating Token Index: 744

Text #14

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1672139 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1252612 (The Pile)

Max Activating Token Index: 713

Text #16

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.2572. Min Act: -0.0000

Data Index: 1645403 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.2342. Min Act: -0.0000

Data Index: 1409379 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.2121. Min Act: -0.0000

Data Index: 153937 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 1.5406. Min Range: -1.5406

Max Act: 1.1931. Min Act: -0.0000

Data Index: 837025 (The Pile)

Max Activating Token Index: 201