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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1832 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.3473. Min Act: -0.0000

Data Index: 97618 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.2589. Min Act: -0.0000

Data Index: 632987 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.2228. Min Act: -0.0000

Data Index: 809161 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.2247. Min Act: -0.0000

Data Index: 836896 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1124163 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0044. Min Act: -0.0000

Data Index: 216374 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1080438 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8423. Min Act: -0.0000

Data Index: 938690 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8695. Min Act: -0.0000

Data Index: 414589 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8695. Min Act: -0.0001

Data Index: 1019668 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8695. Min Act: -0.0000

Data Index: 596071 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1216270 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8587. Min Act: -0.0001

Data Index: 100094 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1103964 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8177. Min Act: -0.0000

Data Index: 137957 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.7969. Min Act: -0.0000

Data Index: 378105 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1114586 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8259. Min Act: -0.0000

Data Index: 240108 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8417. Min Act: -0.0001

Data Index: 49555 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8360. Min Act: -0.0000

Data Index: 570230 (C4 (Web Text))

Max Activating Token Index: 417