Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2317 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1366447 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.8041. Min Act: -0.0000

Data Index: 985571 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.8038. Min Act: -0.0000

Data Index: 75193 (The Pile)

Max Activating Token Index: 337

Text #3

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7937. Min Act: -0.0000

Data Index: 796389 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1740147 (The Pile)

Max Activating Token Index: 54

Text #5

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7260. Min Act: -0.0000

Data Index: 205409 (The Pile)

Max Activating Token Index: 872

Text #6

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1374385 (The Pile)

Max Activating Token Index: 214

Text #7

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6941. Min Act: -0.0000

Data Index: 793742 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7134. Min Act: -0.0000

Data Index: 458298 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1445319 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1539623 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1648857 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7288. Min Act: -0.0000

Data Index: 426035 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7078. Min Act: -0.0000

Data Index: 362532 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6976. Min Act: -0.0000

Data Index: 82863 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6964. Min Act: -0.0000

Data Index: 681103 (The Pile)

Max Activating Token Index: 76

Text #16

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6910. Min Act: -0.0001

Data Index: 1649086 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1273755 (The Pile)

Max Activating Token Index: 877

Text #18

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1865741 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1375609 (The Pile)

Max Activating Token Index: 575