Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 283 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7943. Min Act: -0.0000

Data Index: 284811 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1918209 (The Pile)

Max Activating Token Index: 14

Text #2

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1748824 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1761852 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7028. Min Act: -0.0000

Data Index: 714478 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6200. Min Act: -0.0000

Data Index: 17490 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1300994 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1203408 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6457. Min Act: -0.0000

Data Index: 198136 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1050523 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1101070 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1782048 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1050166 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1146453 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1481366 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1848049 (The Pile)

Max Activating Token Index: 207

Text #16

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6098. Min Act: -0.0000

Data Index: 548446 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1693695 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1126205 (The Pile)

Max Activating Token Index: 879

Text #19

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6162. Min Act: -0.0000

Data Index: 55843 (The Pile)

Max Activating Token Index: 725