Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1005 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1531. Min Act: -0.0006

Data Index: 541721 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1350. Min Act: -0.0006

Data Index: 127576 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1438. Min Act: -0.0006

Data Index: 888849 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1377. Min Act: -0.0006

Data Index: 1326470 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1145. Min Act: -0.0005

Data Index: 603189 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1168. Min Act: -0.0006

Data Index: 1228319 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1168. Min Act: -0.0006

Data Index: 344460 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1114. Min Act: -0.0006

Data Index: 521561 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1144. Min Act: -0.0005

Data Index: 791546 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1084. Min Act: -0.0005

Data Index: 1308514 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1116. Min Act: -0.0006

Data Index: 28613 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1109. Min Act: -0.0006

Data Index: 1309739 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1094. Min Act: -0.0006

Data Index: 176489 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1088. Min Act: -0.0006

Data Index: 685037 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1082. Min Act: -0.0005

Data Index: 889628 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1034. Min Act: -0.0006

Data Index: 723663 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1037. Min Act: -0.0006

Data Index: 883913 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1011. Min Act: -0.0006

Data Index: 806215 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1091. Min Act: -0.0006

Data Index: 1246170 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0965. Min Act: -0.0006

Data Index: 1032616 (C4 (Web Text))

Max Activating Token Index: 863