Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6089 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.4151. Min Act: -0.0000

Data Index: 586370 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.3775. Min Act: -0.0000

Data Index: 1258670 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.3094. Min Act: -0.0000

Data Index: 434165 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.1669. Min Act: -0.0000

Data Index: 580603 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.9033. Min Act: -0.0000

Data Index: 1262271 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.1166. Min Act: -0.0000

Data Index: 1056012 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.1195. Min Act: -0.0000

Data Index: 414257 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.0947. Min Act: -0.0000

Data Index: 1654232 (Python Code)

Max Activating Token Index: 503

Text #8

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.0146. Min Act: -0.0000

Data Index: 1186484 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.8662. Min Act: -0.0000

Data Index: 239074 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.9599. Min Act: -0.0000

Data Index: 966441 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.8435. Min Act: -0.0000

Data Index: 456752 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.8488. Min Act: -0.0000

Data Index: 733276 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.8691. Min Act: -0.0000

Data Index: 457198 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.8460. Min Act: -0.0000

Data Index: 1587326 (Python Code)

Max Activating Token Index: 805

Text #15

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.7950. Min Act: -0.0000

Data Index: 1146883 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.7854. Min Act: -0.0000

Data Index: 372407 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.6604. Min Act: -0.0000

Data Index: 219707 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.7696. Min Act: -0.0000

Data Index: 753301 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.7680. Min Act: -0.0000

Data Index: 117303 (C4 (Web Text))

Max Activating Token Index: 824