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

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

Neuron 2218 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: 1.7538. Min Range: -1.7538

Max Act: 1.7538. Min Act: -0.0001

Data Index: 1394134 (Python Code)

Max Activating Token Index: 920

Text #1

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6810. Min Act: -0.0001

Data Index: 1450227 (Python Code)

Max Activating Token Index: 882

Text #2

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6383. Min Act: -0.0001

Data Index: 1633870 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6373. Min Act: -0.0001

Data Index: 1638188 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.5802. Min Act: -0.0001

Data Index: 1360334 (Python Code)

Max Activating Token Index: 960

Text #5

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.4970. Min Act: -0.0001

Data Index: 1457274 (Python Code)

Max Activating Token Index: 942

Text #6

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.4449. Min Act: -0.0001

Data Index: 1365480 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.5266. Min Act: -0.0001

Data Index: 1562620 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.3910. Min Act: -0.0001

Data Index: 1461620 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.3605. Min Act: -0.0001

Data Index: 1602593 (Python Code)

Max Activating Token Index: 763

Text #10

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.4009. Min Act: -0.0001

Data Index: 1619439 (Python Code)

Max Activating Token Index: 475

Text #11

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.3449. Min Act: -0.0001

Data Index: 1454375 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.1801. Min Act: -0.0001

Data Index: 1502101 (Python Code)

Max Activating Token Index: 664

Text #13

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.3309. Min Act: -0.0001

Data Index: 1370007 (Python Code)

Max Activating Token Index: 604

Text #14

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.3710. Min Act: -0.0001

Data Index: 1500675 (Python Code)

Max Activating Token Index: 997

Text #15

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.2507. Min Act: -0.0001

Data Index: 1380911 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.4793. Min Act: -0.0001

Data Index: 1607208 (Python Code)

Max Activating Token Index: 542

Text #17

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.2802. Min Act: -0.0001

Data Index: 1471288 (Python Code)

Max Activating Token Index: 753

Text #18

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.3254. Min Act: -0.0001

Data Index: 1573735 (Python Code)

Max Activating Token Index: 322

Text #19

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.3603. Min Act: -0.0001

Data Index: 1424996 (Python Code)

Max Activating Token Index: 672