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

Dataset: The Pile

Neuron 44 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1095244 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.5731. Min Act: -0.0000

Data Index: 430017 (The Pile)

Max Activating Token Index: 910

Text #2

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.5048. Min Act: -0.0000

Data Index: 936257 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1474214 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1278372 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4747. Min Act: -0.0000

Data Index: 168935 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4428. Min Act: -0.0000

Data Index: 919945 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1325134 (The Pile)

Max Activating Token Index: 716

Text #8

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4410. Min Act: -0.0000

Data Index: 237538 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1500059 (The Pile)

Max Activating Token Index: 950

Text #10

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1276140 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4083. Min Act: -0.0000

Data Index: 367380 (The Pile)

Max Activating Token Index: 745

Text #12

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4338. Min Act: -0.0000

Data Index: 95138 (The Pile)

Max Activating Token Index: 880

Text #13

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1716467 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1284774 (The Pile)

Max Activating Token Index: 877

Text #15

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.3978. Min Act: -0.0000

Data Index: 844673 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1767063 (The Pile)

Max Activating Token Index: 959

Text #17

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4148. Min Act: 0.0000

Data Index: 180764 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1655580 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 0.6612. Min Range: -0.6612

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1533136 (The Pile)

Max Activating Token Index: 778