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

Dataset: The Pile

Neuron 487 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0131. Min Range: -1.0131

Max Act: 1.0131. Min Act: -0.0000

Data Index: 577172 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1696595 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1048957 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.9017. Min Act: -0.0000

Data Index: 1002058 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1078202 (The Pile)

Max Activating Token Index: 297

Text #5

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1646413 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.8397. Min Act: -0.0000

Data Index: 338860 (The Pile)

Max Activating Token Index: 254

Text #7

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1556561 (The Pile)

Max Activating Token Index: 723

Text #8

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1647995 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.7668. Min Act: -0.0000

Data Index: 1116128 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.8370. Min Act: -0.0000

Data Index: 411235 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1159966 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1276809 (The Pile)

Max Activating Token Index: 340

Text #13

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1189891 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1823414 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.7489. Min Act: -0.0000

Data Index: 452306 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.7675. Min Act: -0.0000

Data Index: 480944 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.7390. Min Act: -0.0000

Data Index: 281781 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.7300. Min Act: -0.0000

Data Index: 225775 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 1.0131. Min Range: -1.0131

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1100128 (The Pile)

Max Activating Token Index: 779