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

Dataset: The Pile

Neuron 3141 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: 1.4187. Min Range: -1.4187

Max Act: 1.4187. Min Act: -0.0000

Data Index: 384335 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.9982. Min Act: -0.0000

Data Index: 184767 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.9608. Min Act: -0.0000

Data Index: 1314497 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.9107. Min Act: -0.0000

Data Index: 251837 (The Pile)

Max Activating Token Index: 941

Text #4

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1205043 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8275. Min Act: -0.0001

Data Index: 718033 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1327554 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8119. Min Act: -0.0000

Data Index: 875509 (The Pile)

Max Activating Token Index: 899

Text #8

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1399289 (The Pile)

Max Activating Token Index: 32

Text #9

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8555. Min Act: -0.0000

Data Index: 644644 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8018. Min Act: -0.0000

Data Index: 880398 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1503318 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.6646. Min Act: -0.0000

Data Index: 166530 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.7203. Min Act: -0.0000

Data Index: 879639 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1606647 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.7414. Min Act: -0.0000

Data Index: 227373 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1926356 (The Pile)

Max Activating Token Index: 935

Text #17

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.7400. Min Act: -0.0000

Data Index: 386395 (The Pile)

Max Activating Token Index: 572

Text #18

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1614956 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.7582. Min Act: -0.0000

Data Index: 24528 (The Pile)

Max Activating Token Index: 1008