Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4055 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0661. Min Range: -1.0661

Max Act: 1.0661. Min Act: -0.0001

Data Index: 1578100 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1618956 (Python Code)

Max Activating Token Index: 696

Text #2

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1612148 (Python Code)

Max Activating Token Index: 969

Text #3

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1543630 (Python Code)

Max Activating Token Index: 593

Text #4

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1408953 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1493900 (Python Code)

Max Activating Token Index: 84

Text #6

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1417020 (Python Code)

Max Activating Token Index: 841

Text #7

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1488595 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1412237 (Python Code)

Max Activating Token Index: 360

Text #9

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1525835 (Python Code)

Max Activating Token Index: 835

Text #10

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1401261 (Python Code)

Max Activating Token Index: 149

Text #11

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1563521 (Python Code)

Max Activating Token Index: 545

Text #12

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1495651 (Python Code)

Max Activating Token Index: 610

Text #13

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1415434 (Python Code)

Max Activating Token Index: 661

Text #14

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1547324 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1458080 (Python Code)

Max Activating Token Index: 779

Text #16

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1645487 (Python Code)

Max Activating Token Index: 795

Text #17

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1471718 (Python Code)

Max Activating Token Index: 519

Text #18

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1527950 (Python Code)

Max Activating Token Index: 325

Text #19

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1498149 (Python Code)

Max Activating Token Index: 233