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

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

Neuron 3930 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1109586 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.8601. Min Act: -0.0000

Data Index: 59942 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.8594. Min Act: -0.0000

Data Index: 400130 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.8476. Min Act: -0.0000

Data Index: 578513 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.8070. Min Act: -0.0000

Data Index: 137575 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7483. Min Act: -0.0000

Data Index: 913391 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7569. Min Act: -0.0000

Data Index: 440172 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1045640 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1172321 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7229. Min Act: -0.0000

Data Index: 1083433 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1093687 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7237. Min Act: -0.0000

Data Index: 755958 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6761. Min Act: -0.0000

Data Index: 257139 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6699. Min Act: -0.0000

Data Index: 77917 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1166602 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1104579 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6272. Min Act: -0.0000

Data Index: 873129 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1109822 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6272. Min Act: -0.0000

Data Index: 426222 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6155. Min Act: -0.0000

Data Index: 437006 (C4 (Web Text))

Max Activating Token Index: 703