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

Dataset: The Pile

Neuron 3109 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: 0.4031. Min Range: -0.4031

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1517785 (The Pile)

Max Activating Token Index: 894

Text #1

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1798548 (The Pile)

Max Activating Token Index: 844

Text #2

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3219. Min Act: -0.0000

Data Index: 412949 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1526600 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1196413 (The Pile)

Max Activating Token Index: 847

Text #5

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1622967 (The Pile)

Max Activating Token Index: 903

Text #6

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2924. Min Act: -0.0000

Data Index: 962812 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1106077 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2715. Min Act: -0.0000

Data Index: 244975 (The Pile)

Max Activating Token Index: 784

Text #9

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1742244 (The Pile)

Max Activating Token Index: 380

Text #10

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1741815 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1074993 (The Pile)

Max Activating Token Index: 925

Text #12

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2831. Min Act: -0.0000

Data Index: 636275 (The Pile)

Max Activating Token Index: 999

Text #13

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2509. Min Act: -0.0000

Data Index: 277989 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2770. Min Act: -0.0000

Data Index: 55549 (The Pile)

Max Activating Token Index: 800

Text #15

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2621. Min Act: -0.0000

Data Index: 318113 (The Pile)

Max Activating Token Index: 398

Text #16

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1745588 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1630674 (The Pile)

Max Activating Token Index: 979

Text #18

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1529544 (The Pile)

Max Activating Token Index: 846

Text #19

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1581495 (The Pile)

Max Activating Token Index: 970