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

Dataset: The Pile

Neuron 4031 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4713. Min Range: -3.4713

Max Act: 3.4713. Min Act: -0.0000

Data Index: 406635 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 3.4713. Min Range: -3.4713

Max Act: 3.3280. Min Act: -0.0000

Data Index: 1481041 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 3.4713. Min Range: -3.4713

Max Act: 3.4633. Min Act: -0.0000

Data Index: 1382447 (The Pile)

Max Activating Token Index: 615

Text #3

Max Range: 3.4713. Min Range: -3.4713

Max Act: 3.2864. Min Act: -0.0000

Data Index: 794264 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 3.4713. Min Range: -3.4713

Max Act: 3.1026. Min Act: -0.0000

Data Index: 495568 (The Pile)

Max Activating Token Index: 959

Text #5

Max Range: 3.4713. Min Range: -3.4713

Max Act: 3.0732. Min Act: -0.0000

Data Index: 453110 (The Pile)

Max Activating Token Index: 465

Text #6

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.9157. Min Act: -0.0000

Data Index: 370094 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.9030. Min Act: -0.0000

Data Index: 452320 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 3.4713. Min Range: -3.4713

Max Act: 3.1641. Min Act: -0.0000

Data Index: 314122 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.9974. Min Act: -0.0000

Data Index: 1715369 (The Pile)

Max Activating Token Index: 508

Text #10

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.8070. Min Act: -0.0000

Data Index: 1547073 (The Pile)

Max Activating Token Index: 880

Text #11

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.9173. Min Act: -0.0000

Data Index: 1628049 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.7939. Min Act: -0.0000

Data Index: 676597 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.5096. Min Act: -0.0000

Data Index: 1243017 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.6459. Min Act: -0.0000

Data Index: 655944 (The Pile)

Max Activating Token Index: 300

Text #15

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.9036. Min Act: -0.0000

Data Index: 1706274 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.8662. Min Act: -0.0000

Data Index: 372898 (The Pile)

Max Activating Token Index: 942

Text #17

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.6739. Min Act: -0.0000

Data Index: 693249 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.6443. Min Act: -0.0000

Data Index: 271183 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 3.4713. Min Range: -3.4713

Max Act: 2.6518. Min Act: -0.0000

Data Index: 41136 (The Pile)

Max Activating Token Index: 917