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

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

Neuron 1829 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1105763 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1280. Min Act: -0.0001

Data Index: 435771 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1348. Min Act: -0.0000

Data Index: 271515 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1204. Min Act: -0.0001

Data Index: 505548 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1218. Min Act: -0.0000

Data Index: 976249 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1300. Min Act: -0.0001

Data Index: 167445 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1158. Min Act: -0.0001

Data Index: 581178 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1103881 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1035. Min Act: -0.0000

Data Index: 706744 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1325955 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0994. Min Act: -0.0000

Data Index: 321146 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0985. Min Act: -0.0000

Data Index: 950051 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1103. Min Act: -0.0000

Data Index: 741135 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1190058 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1302529 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.1048. Min Act: -0.0001

Data Index: 368826 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1209550 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0976. Min Act: -0.0000

Data Index: 70433 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1015122 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.1495. Min Range: -0.1495

Max Act: 0.0929. Min Act: -0.0000

Data Index: 292086 (C4 (Web Text))

Max Activating Token Index: 585