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

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

Neuron 1302 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: 0.7603. Min Range: -0.7603

Max Act: 0.7603. Min Act: -0.0001

Data Index: 1556840 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7090. Min Act: -0.0001

Data Index: 1451768 (Python Code)

Max Activating Token Index: 624

Text #2

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6304. Min Act: -0.0001

Data Index: 1480096 (Python Code)

Max Activating Token Index: 274

Text #3

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6711. Min Act: -0.0001

Data Index: 1424602 (Python Code)

Max Activating Token Index: 288

Text #4

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6670. Min Act: -0.0001

Data Index: 1382940 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1571776 (Python Code)

Max Activating Token Index: 471

Text #6

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6851. Min Act: -0.0001

Data Index: 1487549 (Python Code)

Max Activating Token Index: 101

Text #7

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6450. Min Act: -0.0001

Data Index: 1569295 (Python Code)

Max Activating Token Index: 330

Text #8

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7116. Min Act: -0.0001

Data Index: 1519816 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6475. Min Act: -0.0001

Data Index: 1495758 (Python Code)

Max Activating Token Index: 347

Text #10

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6396. Min Act: -0.0001

Data Index: 1605459 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6566. Min Act: -0.0001

Data Index: 1507530 (Python Code)

Max Activating Token Index: 389

Text #12

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6337. Min Act: -0.0001

Data Index: 1616185 (Python Code)

Max Activating Token Index: 446

Text #13

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6316. Min Act: -0.0001

Data Index: 1604416 (Python Code)

Max Activating Token Index: 780

Text #14

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1431270 (Python Code)

Max Activating Token Index: 669

Text #15

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.7072. Min Act: -0.0001

Data Index: 1534164 (Python Code)

Max Activating Token Index: 196

Text #16

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6178. Min Act: -0.0001

Data Index: 1583140 (Python Code)

Max Activating Token Index: 913

Text #17

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6058. Min Act: -0.0001

Data Index: 1381733 (Python Code)

Max Activating Token Index: 722

Text #18

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6835. Min Act: -0.0001

Data Index: 1508058 (Python Code)

Max Activating Token Index: 713

Text #19

Max Range: 0.7603. Min Range: -0.7603

Max Act: 0.6691. Min Act: -0.0001

Data Index: 1593776 (Python Code)

Max Activating Token Index: 817