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

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

Neuron 56 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: 0.1246. Min Range: -0.1246

Max Act: 0.1246. Min Act: -0.0001

Data Index: 914857 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1043035 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1058992 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1343508 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1006343 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1063. Min Act: -0.0001

Data Index: 823635 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1058. Min Act: -0.0001

Data Index: 572374 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1088. Min Act: -0.0001

Data Index: 151279 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0990. Min Act: -0.0001

Data Index: 965427 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1026. Min Act: -0.0001

Data Index: 446325 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0987. Min Act: -0.0001

Data Index: 293935 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1001. Min Act: -0.0001

Data Index: 224458 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1001. Min Act: -0.0001

Data Index: 452844 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0961. Min Act: -0.0001

Data Index: 107020 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0964. Min Act: -0.0001

Data Index: 330084 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0990. Min Act: -0.0001

Data Index: 198406 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1023. Min Act: -0.0001

Data Index: 990471 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0987. Min Act: -0.0001

Data Index: 975836 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1087008 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1289368 (C4 (Web Text))

Max Activating Token Index: 483