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

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

Neuron 4573 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: 3.9943. Min Range: -3.9943

Max Act: 3.9943. Min Act: -0.0001

Data Index: 1077883 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.7582. Min Act: -0.0000

Data Index: 280132 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.7098. Min Act: -0.0000

Data Index: 1297625 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.6285. Min Act: -0.0000

Data Index: 796027 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.5047. Min Act: -0.0000

Data Index: 285358 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.1618. Min Act: -0.0000

Data Index: 223695 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.2520. Min Act: -0.0000

Data Index: 562066 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.3444. Min Act: -0.0000

Data Index: 227931 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.2273. Min Act: -0.0000

Data Index: 1241848 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.3218. Min Act: -0.0000

Data Index: 1196992 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.1572. Min Act: -0.0000

Data Index: 839457 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.1274. Min Act: -0.0000

Data Index: 840664 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.1234. Min Act: -0.0000

Data Index: 1241052 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 3.9943. Min Range: -3.9943

Max Act: 3.0968. Min Act: -0.0000

Data Index: 574457 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 3.9943. Min Range: -3.9943

Max Act: 2.8510. Min Act: -0.0000

Data Index: 1033703 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 3.9943. Min Range: -3.9943

Max Act: 2.8043. Min Act: -0.0000

Data Index: 328195 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 3.9943. Min Range: -3.9943

Max Act: 2.7946. Min Act: -0.0000

Data Index: 29665 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 3.9943. Min Range: -3.9943

Max Act: 2.8706. Min Act: -0.0000

Data Index: 147615 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 3.9943. Min Range: -3.9943

Max Act: 2.8890. Min Act: -0.0000

Data Index: 160364 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 3.9943. Min Range: -3.9943

Max Act: 2.6992. Min Act: -0.0001

Data Index: 1281750 (C4 (Web Text))

Max Activating Token Index: 276