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

Dataset: The Pile

Neuron 3414 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: 0.4320. Min Range: -0.4320

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1510725 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1348960 (The Pile)

Max Activating Token Index: 516

Text #2

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1883297 (The Pile)

Max Activating Token Index: 43

Text #3

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1134177 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2819. Min Act: -0.0000

Data Index: 208771 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1959088 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2885. Min Act: -0.0000

Data Index: 852436 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3126. Min Act: -0.0000

Data Index: 553749 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2678. Min Act: -0.0000

Data Index: 949804 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2532. Min Act: -0.0000

Data Index: 325685 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2989. Min Act: -0.0000

Data Index: 237478 (The Pile)

Max Activating Token Index: 277

Text #11

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1746337 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2835. Min Act: -0.0000

Data Index: 869599 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2632. Min Act: -0.0000

Data Index: 728441 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1616284 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2420. Min Act: -0.0000

Data Index: 961673 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1563669 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1602534 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1211169 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2498. Min Act: -0.0000

Data Index: 277252 (The Pile)

Max Activating Token Index: 112