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

Dataset: The Pile

Neuron 2930 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.8000. Min Act: -0.0000

Data Index: 395964 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.7446. Min Act: -0.0000

Data Index: 617019 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.7913. Min Act: -0.0000

Data Index: 793085 (The Pile)

Max Activating Token Index: 444

Text #3

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1744256 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1181115 (The Pile)

Max Activating Token Index: 188

Text #5

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6796. Min Act: -0.0000

Data Index: 862513 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6908. Min Act: -0.0000

Data Index: 734607 (The Pile)

Max Activating Token Index: 563

Text #7

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1136057 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1933698 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6983. Min Act: -0.0000

Data Index: 637107 (The Pile)

Max Activating Token Index: 652

Text #10

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1707898 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.7319. Min Act: -0.0000

Data Index: 485716 (The Pile)

Max Activating Token Index: 554

Text #12

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6488. Min Act: -0.0000

Data Index: 626359 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6368. Min Act: -0.0000

Data Index: 440018 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6929. Min Act: -0.0000

Data Index: 463847 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6699. Min Act: -0.0000

Data Index: 178803 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1220084 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1068746 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6640. Min Act: -0.0000

Data Index: 231830 (The Pile)

Max Activating Token Index: 7

Text #19

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6788. Min Act: -0.0000

Data Index: 733106 (The Pile)

Max Activating Token Index: 351