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

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

Neuron 1955 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8339. Min Act: -0.0001

Data Index: 1208372 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8303. Min Act: -0.0001

Data Index: 1374560 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8268. Min Act: -0.0001

Data Index: 1613972 (Python Code)

Max Activating Token Index: 552

Text #3

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8089. Min Act: -0.0001

Data Index: 1407712 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8411. Min Act: -0.0001

Data Index: 1104989 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8308. Min Act: -0.0001

Data Index: 1403269 (Python Code)

Max Activating Token Index: 633

Text #6

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8087. Min Act: -0.0001

Data Index: 1526349 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7071. Min Act: -0.0001

Data Index: 1532656 (Python Code)

Max Activating Token Index: 613

Text #8

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8445. Min Act: -0.0001

Data Index: 1580701 (Python Code)

Max Activating Token Index: 115

Text #9

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7457. Min Act: -0.0001

Data Index: 1541428 (Python Code)

Max Activating Token Index: 654

Text #10

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8014. Min Act: -0.0001

Data Index: 1389570 (Python Code)

Max Activating Token Index: 508

Text #11

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8069. Min Act: -0.0001

Data Index: 1576980 (Python Code)

Max Activating Token Index: 377

Text #12

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7658. Min Act: -0.0001

Data Index: 861347 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7888. Min Act: -0.0001

Data Index: 1501916 (Python Code)

Max Activating Token Index: 521

Text #14

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7404. Min Act: -0.0001

Data Index: 1407243 (Python Code)

Max Activating Token Index: 895

Text #15

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7097. Min Act: -0.0001

Data Index: 1552277 (Python Code)

Max Activating Token Index: 462

Text #16

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6455. Min Act: -0.0001

Data Index: 1413434 (Python Code)

Max Activating Token Index: 921

Text #17

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8020. Min Act: -0.0001

Data Index: 1508911 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7450. Min Act: -0.0001

Data Index: 1619286 (Python Code)

Max Activating Token Index: 515

Text #19

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7022. Min Act: -0.0001

Data Index: 1488624 (Python Code)

Max Activating Token Index: 654