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

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

Neuron 2142 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.4951. Min Act: -0.0000

Data Index: 1570868 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.4557. Min Act: -0.0000

Data Index: 1466402 (Python Code)

Max Activating Token Index: 352

Text #2

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.2976. Min Act: -0.0000

Data Index: 1628271 (Python Code)

Max Activating Token Index: 841

Text #3

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.2515. Min Act: -0.0000

Data Index: 1579284 (Python Code)

Max Activating Token Index: 135

Text #4

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.2019. Min Act: -0.0000

Data Index: 1491393 (Python Code)

Max Activating Token Index: 865

Text #5

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.8366. Min Act: -0.0000

Data Index: 1634982 (Python Code)

Max Activating Token Index: 986

Text #6

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.0318. Min Act: -0.0000

Data Index: 1528847 (Python Code)

Max Activating Token Index: 688

Text #7

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.0239. Min Act: -0.0000

Data Index: 1530025 (Python Code)

Max Activating Token Index: 298

Text #8

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.0179. Min Act: -0.0000

Data Index: 1617458 (Python Code)

Max Activating Token Index: 781

Text #9

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.1043. Min Act: -0.0000

Data Index: 1448216 (Python Code)

Max Activating Token Index: 544

Text #10

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.8690. Min Act: -0.0000

Data Index: 1363667 (Python Code)

Max Activating Token Index: 631

Text #11

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.9518. Min Act: -0.0000

Data Index: 1597616 (Python Code)

Max Activating Token Index: 438

Text #12

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.8812. Min Act: -0.0000

Data Index: 1641239 (Python Code)

Max Activating Token Index: 263

Text #13

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.8704. Min Act: -0.0000

Data Index: 1551984 (Python Code)

Max Activating Token Index: 550

Text #14

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.7618. Min Act: -0.0000

Data Index: 1384707 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.8075. Min Act: -0.0000

Data Index: 1633672 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.8139. Min Act: -0.0000

Data Index: 1598638 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.9043. Min Act: -0.0000

Data Index: 1453498 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.7968. Min Act: -0.0000

Data Index: 1404374 (Python Code)

Max Activating Token Index: 841

Text #19

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.7324. Min Act: -0.0000

Data Index: 1383358 (Python Code)

Max Activating Token Index: 835