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

Dataset: The Pile

Neuron 1144 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4906. Min Range: -4.4906

Max Act: 4.4906. Min Act: -0.0000

Data Index: 761973 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.9921. Min Act: -0.0000

Data Index: 263462 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 4.4906. Min Range: -4.4906

Max Act: 4.1620. Min Act: -0.0000

Data Index: 1099931 (The Pile)

Max Activating Token Index: 941

Text #3

Max Range: 4.4906. Min Range: -4.4906

Max Act: 4.1108. Min Act: -0.0000

Data Index: 1352153 (The Pile)

Max Activating Token Index: 344

Text #4

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.8837. Min Act: -0.0000

Data Index: 1379334 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.7300. Min Act: -0.0000

Data Index: 930002 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.8691. Min Act: -0.0000

Data Index: 1755160 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.6431. Min Act: -0.0000

Data Index: 867546 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.9666. Min Act: -0.0000

Data Index: 454165 (The Pile)

Max Activating Token Index: 797

Text #9

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.7449. Min Act: -0.0000

Data Index: 1934145 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.7122. Min Act: -0.0000

Data Index: 1671843 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.7242. Min Act: -0.0000

Data Index: 1682772 (The Pile)

Max Activating Token Index: 740

Text #12

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.6967. Min Act: -0.0000

Data Index: 1426601 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.5273. Min Act: -0.0000

Data Index: 1422965 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.6680. Min Act: -0.0000

Data Index: 929006 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.8387. Min Act: -0.0000

Data Index: 121526 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.6554. Min Act: -0.0000

Data Index: 204353 (The Pile)

Max Activating Token Index: 269

Text #17

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.6267. Min Act: -0.0000

Data Index: 1123696 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.6118. Min Act: -0.0000

Data Index: 1599209 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 4.4906. Min Range: -4.4906

Max Act: 3.7636. Min Act: -0.0000

Data Index: 1378106 (The Pile)

Max Activating Token Index: 170