Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 772 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.7900. Min Act: -0.0001

Data Index: 771429 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.7790. Min Act: -0.0001

Data Index: 1105063 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.8050. Min Act: -0.0001

Data Index: 241110 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.8217. Min Act: -0.0001

Data Index: 499599 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6799. Min Act: -0.0001

Data Index: 883369 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6626. Min Act: -0.0001

Data Index: 913974 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6199. Min Act: -0.0001

Data Index: 259074 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6288. Min Act: -0.0001

Data Index: 217255 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5984. Min Act: -0.0001

Data Index: 462464 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5646. Min Act: -0.0001

Data Index: 331787 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5854. Min Act: -0.0001

Data Index: 579251 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5587. Min Act: -0.0001

Data Index: 1009136 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5166. Min Act: -0.0001

Data Index: 1292080 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4903. Min Act: -0.0001

Data Index: 1221600 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5892. Min Act: -0.0001

Data Index: 88555 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5543. Min Act: -0.0001

Data Index: 1051403 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5686. Min Act: -0.0001

Data Index: 1286370 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5291. Min Act: -0.0001

Data Index: 1290715 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5746. Min Act: -0.0001

Data Index: 985583 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5182. Min Act: -0.0001

Data Index: 169575 (C4 (Web Text))

Max Activating Token Index: 60