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

Dataset: The Pile

Neuron 2326 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0413. Min Range: -1.0413

Max Act: 1.0413. Min Act: -0.0001

Data Index: 741062 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9972. Min Act: -0.0000

Data Index: 481349 (The Pile)

Max Activating Token Index: 6

Text #2

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1292097 (The Pile)

Max Activating Token Index: 6

Text #3

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9977. Min Act: -0.0000

Data Index: 800396 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1925984 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9312. Min Act: -0.0000

Data Index: 289937 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1306483 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9561. Min Act: -0.0000

Data Index: 115046 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 1.0413. Min Range: -1.0413

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1914678 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9555. Min Act: -0.0000

Data Index: 798356 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1744057 (The Pile)

Max Activating Token Index: 5

Text #11

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8695. Min Act: -0.0000

Data Index: 806201 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1339072 (The Pile)

Max Activating Token Index: 6

Text #13

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8014. Min Act: -0.0000

Data Index: 812101 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8428. Min Act: -0.0000

Data Index: 430449 (The Pile)

Max Activating Token Index: 10

Text #15

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8646. Min Act: -0.0000

Data Index: 234745 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8126. Min Act: -0.0000

Data Index: 710788 (The Pile)

Max Activating Token Index: 5

Text #17

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8070. Min Act: -0.0000

Data Index: 392012 (The Pile)

Max Activating Token Index: 5

Text #18

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8357. Min Act: -0.0000

Data Index: 480866 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7685. Min Act: -0.0000

Data Index: 914990 (The Pile)

Max Activating Token Index: 55