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

Dataset: The Pile

Neuron 2104 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1110500 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1248143 (The Pile)

Max Activating Token Index: 865

Text #2

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.7819. Min Act: -0.0000

Data Index: 28043 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.7206. Min Act: -0.0000

Data Index: 640036 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.7397. Min Act: -0.0000

Data Index: 419518 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1970083 (The Pile)

Max Activating Token Index: 476

Text #6

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.7559. Min Act: -0.0000

Data Index: 981542 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.7385. Min Act: -0.0000

Data Index: 846440 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.6761. Min Act: -0.0000

Data Index: 702265 (The Pile)

Max Activating Token Index: 627

Text #9

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.7165. Min Act: -0.0000

Data Index: 161082 (The Pile)

Max Activating Token Index: 913

Text #10

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.6457. Min Act: 0.0000

Data Index: 384533 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.6470. Min Act: 0.0000

Data Index: 1860360 (The Pile)

Max Activating Token Index: 589

Text #12

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.7344. Min Act: -0.0000

Data Index: 885566 (The Pile)

Max Activating Token Index: 1013

Text #13

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.6330. Min Act: -0.0000

Data Index: 127082 (The Pile)

Max Activating Token Index: 984

Text #14

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1724609 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.6233. Min Act: -0.0000

Data Index: 368316 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1151414 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.7086. Min Act: -0.0000

Data Index: 894332 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1667314 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1290205 (The Pile)

Max Activating Token Index: 505