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

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

Neuron 1607 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1298. Min Act: -0.0002

Data Index: 728242 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1276. Min Act: -0.0002

Data Index: 868951 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1184. Min Act: -0.0002

Data Index: 597213 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1224. Min Act: -0.0002

Data Index: 667363 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1172. Min Act: -0.0002

Data Index: 963619 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1091. Min Act: -0.0002

Data Index: 607221 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1058. Min Act: -0.0002

Data Index: 807809 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1056. Min Act: -0.0002

Data Index: 935269 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1107. Min Act: -0.0002

Data Index: 673884 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1104. Min Act: -0.0002

Data Index: 731720 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1052. Min Act: -0.0002

Data Index: 573932 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1101. Min Act: -0.0002

Data Index: 675013 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1281514 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1155981 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1049. Min Act: -0.0002

Data Index: 798693 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1082. Min Act: -0.0002

Data Index: 606304 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1095252 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0979. Min Act: -0.0002

Data Index: 940501 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0970. Min Act: -0.0002

Data Index: 535368 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0989. Min Act: -0.0002

Data Index: 373499 (C4 (Web Text))

Max Activating Token Index: 101