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

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

Neuron 4308 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1253. Min Act: -0.0000

Data Index: 588513 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1288. Min Act: -0.0000

Data Index: 902852 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1228. Min Act: -0.0000

Data Index: 295447 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1089. Min Act: -0.0000

Data Index: 408658 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1091. Min Act: -0.0000

Data Index: 459774 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1065. Min Act: -0.0000

Data Index: 386227 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0985. Min Act: -0.0000

Data Index: 990377 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1335690 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0979. Min Act: -0.0000

Data Index: 650261 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0913. Min Act: -0.0000

Data Index: 458117 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0975. Min Act: -0.0000

Data Index: 566171 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0988. Min Act: -0.0000

Data Index: 583617 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0974. Min Act: -0.0000

Data Index: 961645 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0955. Min Act: -0.0000

Data Index: 453854 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0945. Min Act: -0.0000

Data Index: 890794 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0889. Min Act: -0.0000

Data Index: 966395 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0859. Min Act: -0.0000

Data Index: 254128 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0883. Min Act: -0.0000

Data Index: 594889 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1329701 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0844. Min Act: -0.0000

Data Index: 658279 (C4 (Web Text))

Max Activating Token Index: 774