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

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

Neuron 3939 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4130. Min Range: -1.4130

Max Act: 1.4130. Min Act: -0.0001

Data Index: 280088 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9904. Min Act: -0.0001

Data Index: 56047 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 1.4130. Min Range: -1.4130

Max Act: 1.0893. Min Act: -0.0001

Data Index: 1439735 (Python Code)

Max Activating Token Index: 469

Text #3

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9738. Min Act: -0.0001

Data Index: 614859 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9869. Min Act: -0.0001

Data Index: 189037 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9604. Min Act: -0.0001

Data Index: 1580498 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9297. Min Act: -0.0001

Data Index: 273033 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9582. Min Act: -0.0001

Data Index: 402823 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.8519. Min Act: -0.0001

Data Index: 46629 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9091. Min Act: -0.0001

Data Index: 1237429 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.8929. Min Act: -0.0001

Data Index: 1553134 (Python Code)

Max Activating Token Index: 229

Text #11

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9263. Min Act: -0.0001

Data Index: 337700 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.8692. Min Act: -0.0001

Data Index: 581961 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9016. Min Act: -0.0001

Data Index: 1457960 (Python Code)

Max Activating Token Index: 767

Text #14

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.8488. Min Act: -0.0001

Data Index: 215471 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.8421. Min Act: -0.0001

Data Index: 187214 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.7818. Min Act: -0.0001

Data Index: 430673 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.8601. Min Act: -0.0001

Data Index: 1371310 (Python Code)

Max Activating Token Index: 656

Text #18

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.8015. Min Act: -0.0001

Data Index: 1485772 (Python Code)

Max Activating Token Index: 523

Text #19

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.8249. Min Act: -0.0001

Data Index: 1243086 (C4 (Web Text))

Max Activating Token Index: 837