Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1759 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1679188 (The Pile)

Max Activating Token Index: 810

Text #1

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.1509. Min Act: -0.0000

Data Index: 199439 (The Pile)

Max Activating Token Index: 816

Text #2

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.1823. Min Act: -0.0000

Data Index: 142155 (The Pile)

Max Activating Token Index: 283

Text #3

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.1126. Min Act: -0.0000

Data Index: 596363 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.2094. Min Act: -0.0000

Data Index: 407362 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.0916. Min Act: -0.0000

Data Index: 1245271 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1278526 (The Pile)

Max Activating Token Index: 521

Text #7

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.0105. Min Act: -0.0000

Data Index: 777437 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1601926 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.7506. Min Act: -0.0000

Data Index: 811122 (The Pile)

Max Activating Token Index: 706

Text #10

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1363433 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.7203. Min Act: -0.0000

Data Index: 791450 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.7648. Min Act: -0.0000

Data Index: 784021 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.6325. Min Act: -0.0000

Data Index: 93201 (The Pile)

Max Activating Token Index: 615

Text #14

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1900429 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.6151. Min Act: -0.0000

Data Index: 407105 (The Pile)

Max Activating Token Index: 904

Text #16

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.5948. Min Act: -0.0000

Data Index: 441090 (The Pile)

Max Activating Token Index: 323

Text #17

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1879213 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1354783 (The Pile)

Max Activating Token Index: 748

Text #19

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1626810 (The Pile)

Max Activating Token Index: 158