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

Dataset: The Pile

Neuron 3341 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: 1.2344. Min Range: -1.2344

Max Act: 1.1304. Min Act: -0.0000

Data Index: 1489497 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.2344. Min Act: -0.0001

Data Index: 1102827 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.1543. Min Act: -0.0000

Data Index: 1010356 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0763. Min Act: -0.0000

Data Index: 987961 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0680. Min Act: -0.0000

Data Index: 76982 (The Pile)

Max Activating Token Index: 391

Text #5

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0403. Min Act: -0.0000

Data Index: 328147 (The Pile)

Max Activating Token Index: 372

Text #6

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0362. Min Act: -0.0000

Data Index: 32075 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.1677. Min Act: -0.0000

Data Index: 573231 (The Pile)

Max Activating Token Index: 225

Text #8

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0057. Min Act: -0.0000

Data Index: 22515 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9649. Min Act: -0.0000

Data Index: 851590 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1320646 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1186999 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0032. Min Act: -0.0000

Data Index: 461912 (The Pile)

Max Activating Token Index: 79

Text #13

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1820553 (The Pile)

Max Activating Token Index: 383

Text #14

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1870269 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1941923 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9513. Min Act: -0.0000

Data Index: 748704 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1135492 (The Pile)

Max Activating Token Index: 920

Text #18

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9093. Min Act: -0.0000

Data Index: 739180 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9758. Min Act: -0.0000

Data Index: 682095 (The Pile)

Max Activating Token Index: 941