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

Dataset: The Pile

Neuron 1723 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.4027. Min Act: -0.0000

Data Index: 342481 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.3922. Min Act: -0.0000

Data Index: 490599 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.3506. Min Act: -0.0000

Data Index: 124392 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.3166. Min Act: -0.0000

Data Index: 1894942 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.2176. Min Act: -0.0000

Data Index: 990064 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.1173. Min Act: -0.0000

Data Index: 781021 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.1370. Min Act: -0.0000

Data Index: 544136 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0542. Min Act: -0.0000

Data Index: 1172298 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1720955 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0068. Min Act: -0.0000

Data Index: 593453 (The Pile)

Max Activating Token Index: 882

Text #10

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0341. Min Act: -0.0000

Data Index: 458700 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1472393 (The Pile)

Max Activating Token Index: 282

Text #12

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1866420 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1975718 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8380. Min Act: -0.0000

Data Index: 185127 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1517510 (The Pile)

Max Activating Token Index: 813

Text #16

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9113. Min Act: 0.0000

Data Index: 1098703 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9046. Min Act: 0.0000

Data Index: 1301557 (The Pile)

Max Activating Token Index: 34

Text #18

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8835. Min Act: -0.0000

Data Index: 859197 (The Pile)

Max Activating Token Index: 979

Text #19

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9098. Min Act: -0.0000

Data Index: 287961 (The Pile)

Max Activating Token Index: 864