Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1518 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1403. Min Act: -0.0001

Data Index: 264546 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1288. Min Act: -0.0001

Data Index: 912343 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1179921 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1171675 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1254. Min Act: -0.0001

Data Index: 109834 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1202. Min Act: -0.0001

Data Index: 487338 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1107. Min Act: -0.0001

Data Index: 346057 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1125. Min Act: -0.0001

Data Index: 486904 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1169. Min Act: -0.0001

Data Index: 309438 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1120. Min Act: -0.0001

Data Index: 944761 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1121. Min Act: -0.0001

Data Index: 735970 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1122. Min Act: -0.0001

Data Index: 634095 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1064. Min Act: -0.0001

Data Index: 807566 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1211663 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1090205 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1065. Min Act: -0.0001

Data Index: 701270 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1026. Min Act: -0.0001

Data Index: 531281 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1032. Min Act: -0.0001

Data Index: 394243 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1234402 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1015. Min Act: -0.0001

Data Index: 224472 (C4 (Web Text))

Max Activating Token Index: 226