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

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

Neuron 4421 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: 1.1401. Min Range: -1.1401

Max Act: 1.1401. Min Act: -0.0000

Data Index: 224204 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 1.1401. Min Range: -1.1401

Max Act: 1.0456. Min Act: -0.0000

Data Index: 31859 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9593. Min Act: -0.0000

Data Index: 535893 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9231. Min Act: -0.0000

Data Index: 1025862 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1309571 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7846. Min Act: -0.0000

Data Index: 170668 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8595. Min Act: -0.0000

Data Index: 755825 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7891. Min Act: -0.0000

Data Index: 677368 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7570. Min Act: -0.0000

Data Index: 930062 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1178613 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7094. Min Act: -0.0000

Data Index: 952592 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.6165. Min Act: -0.0000

Data Index: 882939 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7358. Min Act: -0.0000

Data Index: 147946 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1076387 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7107. Min Act: -0.0000

Data Index: 762759 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.6423. Min Act: -0.0000

Data Index: 601533 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7104. Min Act: -0.0000

Data Index: 181971 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1253394 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1357018 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.6734. Min Act: -0.0000

Data Index: 43142 (C4 (Web Text))

Max Activating Token Index: 506