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

Dataset: The Pile

Neuron 900 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: 1.0503. Min Range: -1.0503

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1765984 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.8091. Min Act: -0.0000

Data Index: 139375 (The Pile)

Max Activating Token Index: 601

Text #2

Max Range: 1.0503. Min Range: -1.0503

Max Act: 1.0503. Min Act: -0.0000

Data Index: 493007 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1118762 (The Pile)

Max Activating Token Index: 919

Text #4

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.8595. Min Act: -0.0000

Data Index: 626964 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1156801 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1515814 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.8385. Min Act: -0.0000

Data Index: 476914 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1308285 (The Pile)

Max Activating Token Index: 636

Text #9

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.8147. Min Act: -0.0000

Data Index: 1227170 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7478. Min Act: -0.0000

Data Index: 465736 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7158. Min Act: -0.0000

Data Index: 473351 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7553. Min Act: -0.0000

Data Index: 656129 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7189. Min Act: -0.0000

Data Index: 41714 (The Pile)

Max Activating Token Index: 244

Text #14

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7070. Min Act: -0.0000

Data Index: 522017 (The Pile)

Max Activating Token Index: 639

Text #15

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1559931 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.6983. Min Act: -0.0000

Data Index: 195076 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1128061 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.6491. Min Act: -0.0000

Data Index: 940433 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1569497 (The Pile)

Max Activating Token Index: 77