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

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

Neuron 2017 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.9246. Min Act: -0.0000

Data Index: 239591 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1353824 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7022. Min Act: -0.0000

Data Index: 693592 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.6823. Min Act: -0.0000

Data Index: 806937 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1026844 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.6061. Min Act: -0.0000

Data Index: 298755 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.6171. Min Act: -0.0000

Data Index: 14605 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1234291 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.5707. Min Act: -0.0000

Data Index: 71129 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1176562 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.6015. Min Act: -0.0000

Data Index: 441617 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1142899 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.5716. Min Act: -0.0000

Data Index: 680029 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.6017. Min Act: -0.0000

Data Index: 538942 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1102150 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.6120. Min Act: -0.0000

Data Index: 325130 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1197282 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1125958 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.5299. Min Act: -0.0000

Data Index: 257444 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1284188 (C4 (Web Text))

Max Activating Token Index: 205