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

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

Neuron 4225 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1081857 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1416. Min Act: -0.0000

Data Index: 42300 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1116. Min Act: -0.0000

Data Index: 438264 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1096. Min Act: -0.0000

Data Index: 272079 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1053. Min Act: -0.0000

Data Index: 274576 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1005. Min Act: -0.0000

Data Index: 102967 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1033. Min Act: -0.0000

Data Index: 114841 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1271866 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1296157 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0983. Min Act: -0.0000

Data Index: 631347 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1149464 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0979. Min Act: -0.0000

Data Index: 233262 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1165014 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1260054 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1102481 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.1027. Min Act: -0.0000

Data Index: 606232 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0957. Min Act: -0.0000

Data Index: 763771 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0920. Min Act: -0.0000

Data Index: 43011 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0953. Min Act: -0.0000

Data Index: 565953 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.1489. Min Range: -0.1489

Max Act: 0.0947. Min Act: -0.0000

Data Index: 136668 (C4 (Web Text))

Max Activating Token Index: 467