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

Dataset: The Pile

Neuron 3440 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: 1.6054. Min Range: -1.6054

Max Act: 1.6054. Min Act: -0.0000

Data Index: 785310 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4316. Min Act: -0.0000

Data Index: 912471 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1579728 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.3484. Min Act: -0.0000

Data Index: 1722318 (The Pile)

Max Activating Token Index: 741

Text #4

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1073. Min Act: -0.0000

Data Index: 1632126 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1733. Min Act: -0.0000

Data Index: 948857 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1562259 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1049. Min Act: -0.0000

Data Index: 1413291 (The Pile)

Max Activating Token Index: 614

Text #8

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1957362 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1255362 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0531. Min Act: -0.0000

Data Index: 633427 (The Pile)

Max Activating Token Index: 619

Text #11

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1059147 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0174. Min Act: -0.0000

Data Index: 806589 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0392. Min Act: -0.0000

Data Index: 145929 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1095. Min Act: -0.0000

Data Index: 103651 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0245. Min Act: -0.0000

Data Index: 1001031 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0590. Min Act: -0.0000

Data Index: 169806 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.8965. Min Act: -0.0001

Data Index: 619257 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1610705 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9950. Min Act: -0.0000

Data Index: 241897 (The Pile)

Max Activating Token Index: 79