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

Dataset: The Pile

Neuron 1611 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: 1.6866. Min Range: -1.6866

Max Act: 1.6866. Min Act: -0.0000

Data Index: 594170 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.0673. Min Act: -0.0000

Data Index: 726958 (The Pile)

Max Activating Token Index: 700

Text #2

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.0890. Min Act: -0.0000

Data Index: 1142018 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.0329. Min Act: -0.0000

Data Index: 67085 (The Pile)

Max Activating Token Index: 993

Text #4

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1536488 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.0000. Min Act: -0.0000

Data Index: 874422 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1992599 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.0110. Min Act: -0.0000

Data Index: 310347 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1471491 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.1675. Min Act: -0.0000

Data Index: 1505964 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1614464 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1602289 (The Pile)

Max Activating Token Index: 615

Text #12

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1337849 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.8608. Min Act: -0.0000

Data Index: 913037 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1891829 (The Pile)

Max Activating Token Index: 193

Text #15

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.7442. Min Act: -0.0000

Data Index: 238286 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.7847. Min Act: 0.0000

Data Index: 1614217 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.6353. Min Act: -0.0000

Data Index: 417656 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.7501. Min Act: -0.0000

Data Index: 223401 (The Pile)

Max Activating Token Index: 112

Text #19

Max Range: 1.6866. Min Range: -1.6866

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1176680 (The Pile)

Max Activating Token Index: 454