Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 348 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1159. Min Act: -0.0001

Data Index: 343373 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1127. Min Act: -0.0001

Data Index: 867370 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1109. Min Act: -0.0001

Data Index: 711717 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1033. Min Act: -0.0001

Data Index: 622332 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1119. Min Act: -0.0001

Data Index: 719433 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1074. Min Act: -0.0001

Data Index: 534560 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1068. Min Act: -0.0001

Data Index: 481756 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1015. Min Act: -0.0001

Data Index: 20823 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1012. Min Act: -0.0001

Data Index: 695450 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0997. Min Act: -0.0001

Data Index: 127908 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1344249 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1079500 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1101. Min Act: -0.0001

Data Index: 1046607 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1012. Min Act: -0.0001

Data Index: 962252 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0929. Min Act: -0.0001

Data Index: 401199 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1260897 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0986. Min Act: -0.0001

Data Index: 19260 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0954. Min Act: -0.0001

Data Index: 189330 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0986. Min Act: -0.0001

Data Index: 392099 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1015. Min Act: -0.0001

Data Index: 58973 (C4 (Web Text))

Max Activating Token Index: 223