Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5089 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3303. Min Range: -1.3303

Max Act: 1.3303. Min Act: -0.0000

Data Index: 1490545 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 1.3303. Min Range: -1.3303

Max Act: 1.1156. Min Act: -0.0000

Data Index: 1645637 (Python Code)

Max Activating Token Index: 745

Text #2

Max Range: 1.3303. Min Range: -1.3303

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1372732 (Python Code)

Max Activating Token Index: 75

Text #3

Max Range: 1.3303. Min Range: -1.3303

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1538347 (Python Code)

Max Activating Token Index: 450

Text #4

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1501382 (Python Code)

Max Activating Token Index: 102

Text #5

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1544273 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9683. Min Act: -0.0000

Data Index: 1538363 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 1.3303. Min Range: -1.3303

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1384603 (Python Code)

Max Activating Token Index: 627

Text #8

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1598290 (Python Code)

Max Activating Token Index: 331

Text #9

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1570694 (Python Code)

Max Activating Token Index: 590

Text #10

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1551474 (Python Code)

Max Activating Token Index: 714

Text #11

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9921. Min Act: -0.0000

Data Index: 1618352 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1561973 (Python Code)

Max Activating Token Index: 133

Text #13

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9033. Min Act: -0.0000

Data Index: 1534651 (Python Code)

Max Activating Token Index: 305

Text #14

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1539693 (Python Code)

Max Activating Token Index: 149

Text #15

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9035. Min Act: -0.0000

Data Index: 1619936 (Python Code)

Max Activating Token Index: 447

Text #16

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1630652 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1418233 (Python Code)

Max Activating Token Index: 631

Text #18

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9865. Min Act: -0.0000

Data Index: 1372135 (Python Code)

Max Activating Token Index: 642

Text #19

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1546888 (Python Code)

Max Activating Token Index: 436