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

Dataset: The Pile

Neuron 1692 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.6584. Min Act: -0.0000

Data Index: 1070932 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5908. Min Act: -0.0000

Data Index: 7419 (The Pile)

Max Activating Token Index: 781

Text #2

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5792. Min Act: -0.0000

Data Index: 75971 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1816217 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.3756. Min Act: -0.0000

Data Index: 109261 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1569693 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1234788 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1764704 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1670170 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.1720. Min Act: -0.0000

Data Index: 506099 (The Pile)

Max Activating Token Index: 824

Text #10

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1520153 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.1489. Min Act: -0.0000

Data Index: 1586095 (The Pile)

Max Activating Token Index: 815

Text #12

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1087714 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1616985 (The Pile)

Max Activating Token Index: 802

Text #14

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.1923. Min Act: -0.0000

Data Index: 1054462 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1565041 (The Pile)

Max Activating Token Index: 64

Text #16

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1742706 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1122963 (The Pile)

Max Activating Token Index: 927

Text #18

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1954590 (The Pile)

Max Activating Token Index: 203

Text #19

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.0175. Min Act: -0.0000

Data Index: 920071 (The Pile)

Max Activating Token Index: 340