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

Dataset: The Pile

Neuron 1217 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4488. Min Act: -0.0000

Data Index: 123232 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3623. Min Act: -0.0000

Data Index: 715226 (The Pile)

Max Activating Token Index: 656

Text #2

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3685. Min Act: -0.0000

Data Index: 606631 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3707. Min Act: -0.0000

Data Index: 71173 (The Pile)

Max Activating Token Index: 296

Text #4

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1505402 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2969. Min Act: -0.0000

Data Index: 728537 (The Pile)

Max Activating Token Index: 260

Text #6

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3452. Min Act: -0.0000

Data Index: 941691 (The Pile)

Max Activating Token Index: 223

Text #7

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2864. Min Act: -0.0000

Data Index: 41169 (The Pile)

Max Activating Token Index: 337

Text #8

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2698. Min Act: -0.0000

Data Index: 146375 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3128. Min Act: -0.0000

Data Index: 493683 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2861. Min Act: -0.0000

Data Index: 251993 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1306875 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3007. Min Act: -0.0000

Data Index: 354209 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1963754 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1865556 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1260281 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1790840 (The Pile)

Max Activating Token Index: 121

Text #17

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2668. Min Act: -0.0000

Data Index: 714489 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2543. Min Act: -0.0000

Data Index: 883874 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.2395. Min Act: -0.0000

Data Index: 360463 (The Pile)

Max Activating Token Index: 747