Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 413 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1266413 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1434. Min Act: -0.0000

Data Index: 631932 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1266353 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1310. Min Act: -0.0000

Data Index: 613223 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1102622 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1039632 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1224. Min Act: -0.0000

Data Index: 496690 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1229. Min Act: -0.0000

Data Index: 129774 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1210. Min Act: -0.0000

Data Index: 896143 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1047198 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1148. Min Act: -0.0000

Data Index: 330140 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1121. Min Act: -0.0000

Data Index: 308421 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1052. Min Act: -0.0000

Data Index: 310800 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1359730 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1064. Min Act: -0.0000

Data Index: 979478 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1084337 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1223173 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0962. Min Act: -0.0000

Data Index: 350186 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1018. Min Act: -0.0001

Data Index: 566217 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0973. Min Act: -0.0000

Data Index: 602028 (C4 (Web Text))

Max Activating Token Index: 94