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

Dataset: The Pile

Neuron 783 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1219519 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.7035. Min Act: -0.0000

Data Index: 192083 (The Pile)

Max Activating Token Index: 565

Text #2

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1376617 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1622319 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1321144 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.6459. Min Act: -0.0000

Data Index: 978711 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1331764 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.6103. Min Act: -0.0000

Data Index: 952812 (The Pile)

Max Activating Token Index: 224

Text #8

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.6168. Min Act: -0.0000

Data Index: 53745 (The Pile)

Max Activating Token Index: 393

Text #9

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1163995 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5847. Min Act: -0.0000

Data Index: 93151 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1328722 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5485. Min Act: -0.0000

Data Index: 607643 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1889715 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5389. Min Act: -0.0000

Data Index: 845455 (The Pile)

Max Activating Token Index: 711

Text #15

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.3834. Min Act: -0.0000

Data Index: 763254 (The Pile)

Max Activating Token Index: 878

Text #16

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5502. Min Act: -0.0000

Data Index: 121098 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1415285 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5748. Min Act: -0.0000

Data Index: 698234 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.4854. Min Act: 0.0000

Data Index: 1330795 (The Pile)

Max Activating Token Index: 820