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

Dataset: The Pile

Neuron 624 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: 0.8311. Min Range: -0.8311

Max Act: 0.8311. Min Act: -0.0000

Data Index: 987671 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1860147 (The Pile)

Max Activating Token Index: 183

Text #2

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7388. Min Act: -0.0000

Data Index: 618084 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7560. Min Act: -0.0000

Data Index: 883534 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6761. Min Act: -0.0000

Data Index: 515673 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6966. Min Act: -0.0000

Data Index: 532717 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1329962 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1359674 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1481651 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1081587 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6090. Min Act: -0.0000

Data Index: 83671 (The Pile)

Max Activating Token Index: 934

Text #11

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6067. Min Act: -0.0000

Data Index: 504902 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1283862 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1716170 (The Pile)

Max Activating Token Index: 816

Text #14

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6161. Min Act: -0.0000

Data Index: 395870 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5900. Min Act: -0.0000

Data Index: 525139 (The Pile)

Max Activating Token Index: 65

Text #16

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5600. Min Act: -0.0000

Data Index: 384439 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5833. Min Act: -0.0000

Data Index: 75955 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1686606 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5851. Min Act: -0.0000

Data Index: 963657 (The Pile)

Max Activating Token Index: 156