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

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

Neuron 1508 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.3148. Min Act: -0.0001

Data Index: 692805 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.2224. Min Act: -0.0001

Data Index: 915483 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.2171. Min Act: -0.0001

Data Index: 948406 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1745. Min Act: -0.0001

Data Index: 1244192 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1091. Min Act: -0.0001

Data Index: 542666 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1555. Min Act: -0.0001

Data Index: 807638 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1772. Min Act: -0.0001

Data Index: 378319 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0876. Min Act: -0.0001

Data Index: 751367 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1340. Min Act: -0.0001

Data Index: 1239674 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1393. Min Act: -0.0001

Data Index: 253429 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1441. Min Act: -0.0001

Data Index: 85506 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0728. Min Act: -0.0001

Data Index: 819800 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1048. Min Act: -0.0001

Data Index: 32777 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 1.3148. Min Range: -1.3148

Max Act: 0.9679. Min Act: -0.0001

Data Index: 557344 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0608. Min Act: -0.0001

Data Index: 384422 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0519. Min Act: -0.0001

Data Index: 731647 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0908. Min Act: -0.0001

Data Index: 590187 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0816. Min Act: -0.0001

Data Index: 1294568 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0479. Min Act: -0.0001

Data Index: 1170412 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0466. Min Act: -0.0001

Data Index: 826400 (C4 (Web Text))

Max Activating Token Index: 5