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

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

Neuron 1358 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0006

Data Index: 381339 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1078784 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0005

Data Index: 887979 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1342471 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0006

Data Index: 174639 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0006

Data Index: 47730 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0006

Data Index: 313856 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0007

Data Index: 203861 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0006

Data Index: 359897 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0006

Data Index: 25395 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1066108 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0006

Data Index: 742812 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0006

Data Index: 729270 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0006

Data Index: 44753 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0006

Data Index: 364095 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0006

Data Index: 974677 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0073. Min Act: -0.0006

Data Index: 1346703 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0006

Data Index: 444162 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0006

Data Index: 434650 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0006

Data Index: 629881 (C4 (Web Text))

Max Activating Token Index: 937