Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2463 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.9973. Min Act: -0.0001

Data Index: 132129 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.8766. Min Act: -0.0001

Data Index: 610639 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.8993. Min Act: -0.0001

Data Index: 296528 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.8077. Min Act: -0.0001

Data Index: 23108 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7711. Min Act: -0.0001

Data Index: 895137 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7836. Min Act: -0.0001

Data Index: 461044 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7320. Min Act: -0.0001

Data Index: 696615 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7057. Min Act: -0.0001

Data Index: 355856 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7466. Min Act: -0.0001

Data Index: 552041 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7226. Min Act: -0.0001

Data Index: 432483 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6992. Min Act: -0.0001

Data Index: 417677 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6895. Min Act: -0.0001

Data Index: 79771 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1354333 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6747. Min Act: -0.0001

Data Index: 1342872 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6888. Min Act: -0.0001

Data Index: 1189531 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6697. Min Act: -0.0001

Data Index: 787655 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6878. Min Act: -0.0001

Data Index: 1190948 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6528. Min Act: -0.0001

Data Index: 418102 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6739. Min Act: -0.0001

Data Index: 375651 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6308. Min Act: -0.0001

Data Index: 123228 (C4 (Web Text))

Max Activating Token Index: 330