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

Dataset: The Pile

Neuron 2206 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.6957. Min Act: -0.0000

Data Index: 403378 (The Pile)

Max Activating Token Index: 314

Text #1

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1701391 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1834854 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.3293. Min Act: -0.0000

Data Index: 483418 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1373265 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.1959. Min Act: -0.0000

Data Index: 866744 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2992. Min Act: -0.0000

Data Index: 993816 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2790. Min Act: -0.0000

Data Index: 521254 (The Pile)

Max Activating Token Index: 418

Text #8

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1722327 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1062953 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1397609 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2037. Min Act: -0.0000

Data Index: 804481 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1912698 (The Pile)

Max Activating Token Index: 699

Text #13

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1656449 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1026852 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2660. Min Act: -0.0000

Data Index: 69413 (The Pile)

Max Activating Token Index: 720

Text #16

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2459. Min Act: -0.0000

Data Index: 905414 (The Pile)

Max Activating Token Index: 504

Text #17

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2320. Min Act: -0.0000

Data Index: 634518 (The Pile)

Max Activating Token Index: 259

Text #18

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.1971. Min Act: -0.0000

Data Index: 964300 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.2227. Min Act: -0.0000

Data Index: 62803 (The Pile)

Max Activating Token Index: 395