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

Dataset: The Pile

Neuron 314 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.5842. Min Act: -0.0000

Data Index: 446275 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.4027. Min Act: -0.0000

Data Index: 491477 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.5126. Min Act: -0.0000

Data Index: 481485 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.4058. Min Act: -0.0000

Data Index: 1150826 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3822. Min Act: -0.0000

Data Index: 1172094 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.4108. Min Act: -0.0000

Data Index: 1527428 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.4030. Min Act: -0.0000

Data Index: 690475 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.2974. Min Act: -0.0000

Data Index: 1569300 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3239. Min Act: -0.0000

Data Index: 10752 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3304. Min Act: -0.0000

Data Index: 1770127 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.4023. Min Act: -0.0000

Data Index: 1650730 (The Pile)

Max Activating Token Index: 820

Text #11

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.2776. Min Act: -0.0000

Data Index: 849572 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.2833. Min Act: -0.0000

Data Index: 720672 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3065. Min Act: -0.0000

Data Index: 1752496 (The Pile)

Max Activating Token Index: 450

Text #14

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1653225 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.2925. Min Act: -0.0000

Data Index: 920942 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3265. Min Act: -0.0000

Data Index: 852206 (The Pile)

Max Activating Token Index: 23

Text #17

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.2090. Min Act: -0.0000

Data Index: 960948 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.2708. Min Act: -0.0000

Data Index: 1569955 (The Pile)

Max Activating Token Index: 389

Text #19

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1747229 (The Pile)

Max Activating Token Index: 520