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

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

Neuron 790 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1800. Min Act: -0.0001

Data Index: 74894 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1310. Min Act: -0.0001

Data Index: 220753 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1345. Min Act: -0.0001

Data Index: 528074 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1321. Min Act: -0.0001

Data Index: 1201070 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1179456 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1017428 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1269. Min Act: -0.0001

Data Index: 112352 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1199. Min Act: -0.0001

Data Index: 590234 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1058. Min Act: -0.0001

Data Index: 204906 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1167. Min Act: -0.0001

Data Index: 814631 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1166. Min Act: -0.0001

Data Index: 154448 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1105. Min Act: -0.0001

Data Index: 172722 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1029166 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1148396 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1099. Min Act: -0.0001

Data Index: 563183 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1073. Min Act: -0.0001

Data Index: 468462 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1086. Min Act: -0.0001

Data Index: 498187 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1090. Min Act: -0.0001

Data Index: 834472 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0976. Min Act: -0.0001

Data Index: 895604 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1290988 (C4 (Web Text))

Max Activating Token Index: 641