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

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

Neuron 1815 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1438. Min Act: -0.0004

Data Index: 677094 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1416. Min Act: -0.0004

Data Index: 1280794 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1411. Min Act: -0.0004

Data Index: 970065 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1407. Min Act: -0.0004

Data Index: 807503 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1405. Min Act: -0.0004

Data Index: 609225 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1441. Min Act: -0.0004

Data Index: 604810 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1385. Min Act: -0.0004

Data Index: 810919 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1327. Min Act: -0.0004

Data Index: 1006258 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1435. Min Act: -0.0004

Data Index: 1084435 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1370. Min Act: -0.0004

Data Index: 749795 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1353. Min Act: -0.0004

Data Index: 484335 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1397. Min Act: -0.0004

Data Index: 789629 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1345. Min Act: -0.0004

Data Index: 934224 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1345. Min Act: -0.0004

Data Index: 666644 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1336. Min Act: -0.0004

Data Index: 852121 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1326. Min Act: -0.0004

Data Index: 974124 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1324. Min Act: -0.0004

Data Index: 598479 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1322. Min Act: -0.0004

Data Index: 1257051 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1320. Min Act: -0.0004

Data Index: 8615 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1318. Min Act: -0.0004

Data Index: 384498 (C4 (Web Text))

Max Activating Token Index: 925