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

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

Neuron 1318 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: 4.1383. Min Range: -4.1383

Max Act: 4.1383. Min Act: -0.0000

Data Index: 765682 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.5119. Min Act: -0.0000

Data Index: 1251439 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.1923. Min Act: -0.0000

Data Index: 1167938 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.1480. Min Act: -0.0000

Data Index: 398015 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.4185. Min Act: -0.0000

Data Index: 810339 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 4.1383. Min Range: -4.1383

Max Act: 2.9183. Min Act: -0.0000

Data Index: 781966 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.3729. Min Act: -0.0000

Data Index: 1230556 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.2094. Min Act: -0.0000

Data Index: 834290 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.3489. Min Act: -0.0000

Data Index: 1191869 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.5089. Min Act: -0.0000

Data Index: 523079 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.1800. Min Act: -0.0000

Data Index: 1015595 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.1914. Min Act: -0.0000

Data Index: 121238 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.1673. Min Act: -0.0000

Data Index: 1320507 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.1420. Min Act: -0.0000

Data Index: 217358 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.0030. Min Act: -0.0000

Data Index: 1235161 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 4.1383. Min Range: -4.1383

Max Act: 2.9669. Min Act: -0.0000

Data Index: 218429 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.1089. Min Act: -0.0000

Data Index: 179316 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.2740. Min Act: -0.0000

Data Index: 1319838 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.1234. Min Act: -0.0000

Data Index: 268616 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 4.1383. Min Range: -4.1383

Max Act: 3.0675. Min Act: -0.0000

Data Index: 1215586 (C4 (Web Text))

Max Activating Token Index: 517