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

Dataset: The Pile

Neuron 1496 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: 3.7884. Min Range: -3.7884

Max Act: 3.7884. Min Act: -0.0000

Data Index: 250697 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.3439. Min Act: -0.0000

Data Index: 740095 (The Pile)

Max Activating Token Index: 226

Text #2

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.6060. Min Act: -0.0000

Data Index: 318971 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.4323. Min Act: -0.0000

Data Index: 979098 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.2997. Min Act: -0.0000

Data Index: 742517 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.2020. Min Act: -0.0000

Data Index: 401743 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.8990. Min Act: -0.0000

Data Index: 1796025 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.2470. Min Act: -0.0000

Data Index: 854577 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0496. Min Act: -0.0000

Data Index: 1313738 (The Pile)

Max Activating Token Index: 572

Text #9

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.6712. Min Act: -0.0000

Data Index: 728600 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.2956. Min Act: -0.0000

Data Index: 419220 (The Pile)

Max Activating Token Index: 88

Text #11

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.3642. Min Act: -0.0000

Data Index: 1403111 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.2377. Min Act: -0.0000

Data Index: 1451694 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.9983. Min Act: -0.0000

Data Index: 138514 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.6930. Min Act: -0.0000

Data Index: 1793450 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.9657. Min Act: -0.0000

Data Index: 1797588 (The Pile)

Max Activating Token Index: 284

Text #16

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.4353. Min Act: -0.0000

Data Index: 1868711 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0398. Min Act: -0.0000

Data Index: 915576 (The Pile)

Max Activating Token Index: 921

Text #18

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0304. Min Act: -0.0000

Data Index: 964563 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.8761. Min Act: -0.0000

Data Index: 1569636 (The Pile)

Max Activating Token Index: 373