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

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

Neuron 5428 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0632. Min Range: -1.0632

Max Act: 1.0632. Min Act: -0.0000

Data Index: 169571 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.8396. Min Act: -0.0000

Data Index: 588990 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1289827 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.9271. Min Act: -0.0000

Data Index: 406619 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1024347 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.8054. Min Act: -0.0000

Data Index: 751413 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.8403. Min Act: -0.0000

Data Index: 529363 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.7703. Min Act: -0.0000

Data Index: 130528 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.7589. Min Act: -0.0000

Data Index: 142292 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1094567 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.7560. Min Act: -0.0000

Data Index: 694857 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.6886. Min Act: -0.0000

Data Index: 245485 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.6893. Min Act: -0.0001

Data Index: 1573711 (Python Code)

Max Activating Token Index: 764

Text #13

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1203867 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.7297. Min Act: -0.0000

Data Index: 763182 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.7145. Min Act: -0.0000

Data Index: 738053 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1004401 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.7170. Min Act: -0.0000

Data Index: 561118 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.7110. Min Act: -0.0000

Data Index: 474703 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.0632. Min Range: -1.0632

Max Act: 0.6638. Min Act: -0.0000

Data Index: 943285 (C4 (Web Text))

Max Activating Token Index: 647