Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2904 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9166. Min Act: -0.0001

Data Index: 882593 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9534. Min Act: -0.0001

Data Index: 431425 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8953. Min Act: -0.0001

Data Index: 738237 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 1.0403. Min Range: -1.0403

Max Act: 1.0403. Min Act: -0.0001

Data Index: 208927 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9326. Min Act: -0.0001

Data Index: 1255566 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9097. Min Act: -0.0001

Data Index: 189519 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8513. Min Act: -0.0001

Data Index: 491520 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9329. Min Act: -0.0001

Data Index: 28851 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8679. Min Act: -0.0001

Data Index: 6685 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8248. Min Act: -0.0001

Data Index: 1200834 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9331. Min Act: -0.0001

Data Index: 565103 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9082. Min Act: -0.0001

Data Index: 988625 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9629. Min Act: -0.0001

Data Index: 426030 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8334. Min Act: -0.0001

Data Index: 263206 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8940. Min Act: -0.0001

Data Index: 140778 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9041. Min Act: -0.0001

Data Index: 977389 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7774. Min Act: -0.0001

Data Index: 640447 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8713. Min Act: -0.0001

Data Index: 335705 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1010924 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7836. Min Act: -0.0001

Data Index: 1021566 (C4 (Web Text))

Max Activating Token Index: 546