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

Dataset: The Pile

Neuron 333 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.7675. Min Act: -0.0000

Data Index: 1728767 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.4428. Min Act: -0.0000

Data Index: 517246 (The Pile)

Max Activating Token Index: 57

Text #2

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1198991 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1510673 (The Pile)

Max Activating Token Index: 181

Text #4

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.3849. Min Act: -0.0000

Data Index: 438626 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.3605. Min Act: -0.0000

Data Index: 866021 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.2341. Min Act: -0.0000

Data Index: 893203 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.3042. Min Act: -0.0000

Data Index: 1718935 (The Pile)

Max Activating Token Index: 919

Text #8

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1022277 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.4584. Min Act: -0.0000

Data Index: 1208240 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.2261. Min Act: -0.0000

Data Index: 602681 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.2794. Min Act: -0.0000

Data Index: 1238115 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.2679. Min Act: -0.0000

Data Index: 713236 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.2727. Min Act: -0.0000

Data Index: 208142 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.1747. Min Act: -0.0000

Data Index: 1176134 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1679335 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.2410. Min Act: -0.0000

Data Index: 371134 (The Pile)

Max Activating Token Index: 927

Text #17

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.1712. Min Act: -0.0000

Data Index: 289310 (The Pile)

Max Activating Token Index: 883

Text #18

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1529164 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 1.7675. Min Range: -1.7675

Max Act: 1.2355. Min Act: -0.0000

Data Index: 551407 (The Pile)

Max Activating Token Index: 474