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

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

Neuron 2132 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.4039. Min Act: -0.0000

Data Index: 1552642 (Python Code)

Max Activating Token Index: 366

Text #1

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.0335. Min Act: -0.0000

Data Index: 1650084 (Python Code)

Max Activating Token Index: 472

Text #2

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.7341. Min Act: -0.0000

Data Index: 1418683 (Python Code)

Max Activating Token Index: 684

Text #3

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.7725. Min Act: -0.0000

Data Index: 1565045 (Python Code)

Max Activating Token Index: 807

Text #4

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.5294. Min Act: -0.0000

Data Index: 1547106 (Python Code)

Max Activating Token Index: 82

Text #5

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.5319. Min Act: -0.0000

Data Index: 1627575 (Python Code)

Max Activating Token Index: 537

Text #6

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.1524. Min Act: -0.0000

Data Index: 1418960 (Python Code)

Max Activating Token Index: 571

Text #7

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.3360. Min Act: -0.0000

Data Index: 1612836 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.0515. Min Act: -0.0000

Data Index: 1419001 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.2695. Min Act: -0.0000

Data Index: 1645010 (Python Code)

Max Activating Token Index: 655

Text #10

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.2609. Min Act: -0.0000

Data Index: 1368591 (Python Code)

Max Activating Token Index: 136

Text #11

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.2673. Min Act: -0.0000

Data Index: 1577963 (Python Code)

Max Activating Token Index: 327

Text #12

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.3820. Min Act: -0.0000

Data Index: 1364865 (Python Code)

Max Activating Token Index: 385

Text #13

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.2400. Min Act: -0.0000

Data Index: 1495651 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.4983. Min Act: -0.0000

Data Index: 1542404 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.1160. Min Act: -0.0000

Data Index: 1571445 (Python Code)

Max Activating Token Index: 963

Text #16

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.3568. Min Act: -0.0000

Data Index: 1363060 (Python Code)

Max Activating Token Index: 907

Text #17

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.0067. Min Act: -0.0000

Data Index: 1605994 (Python Code)

Max Activating Token Index: 807

Text #18

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.2473. Min Act: -0.0000

Data Index: 1429105 (Python Code)

Max Activating Token Index: 844

Text #19

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.0054. Min Act: -0.0000

Data Index: 1486468 (Python Code)

Max Activating Token Index: 682