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

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

Neuron 508 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1307. Min Act: -0.0001

Data Index: 596914 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1098978 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1321. Min Act: -0.0001

Data Index: 510249 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1255698 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1180. Min Act: -0.0001

Data Index: 822768 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1104. Min Act: -0.0001

Data Index: 120104 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1108. Min Act: -0.0001

Data Index: 325474 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1194. Min Act: -0.0001

Data Index: 596451 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1121. Min Act: -0.0001

Data Index: 711182 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1115. Min Act: -0.0001

Data Index: 449625 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1102. Min Act: -0.0001

Data Index: 604789 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1310321 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1071. Min Act: -0.0001

Data Index: 806642 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1276291 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1018. Min Act: -0.0001

Data Index: 873025 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0970. Min Act: -0.0001

Data Index: 545599 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1022. Min Act: -0.0001

Data Index: 498312 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1067. Min Act: -0.0001

Data Index: 325690 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1353364 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0936. Min Act: -0.0001

Data Index: 814307 (C4 (Web Text))

Max Activating Token Index: 608