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

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

Neuron 3336 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.7493. Min Act: -0.0003

Data Index: 1507771 (Python Code)

Max Activating Token Index: 336

Text #1

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.2585. Min Act: -0.0002

Data Index: 1521968 (Python Code)

Max Activating Token Index: 63

Text #2

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.2961. Min Act: -0.0002

Data Index: 1371685 (Python Code)

Max Activating Token Index: 588

Text #3

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.2066. Min Act: -0.0003

Data Index: 1412815 (Python Code)

Max Activating Token Index: 116

Text #4

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.2015. Min Act: -0.0003

Data Index: 1592536 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.1034. Min Act: -0.0003

Data Index: 1375598 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.1868. Min Act: -0.0002

Data Index: 1403461 (Python Code)

Max Activating Token Index: 228

Text #7

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.1607. Min Act: -0.0003

Data Index: 1491812 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.1312. Min Act: -0.0002

Data Index: 1501634 (Python Code)

Max Activating Token Index: 387

Text #9

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.1205. Min Act: -0.0003

Data Index: 1601677 (Python Code)

Max Activating Token Index: 78

Text #10

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.1201. Min Act: -0.0002

Data Index: 1395910 (Python Code)

Max Activating Token Index: 374

Text #11

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.0307. Min Act: -0.0002

Data Index: 1364809 (Python Code)

Max Activating Token Index: 233

Text #12

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.1089. Min Act: -0.0003

Data Index: 1397303 (Python Code)

Max Activating Token Index: 895

Text #13

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.0965. Min Act: -0.0003

Data Index: 1639653 (Python Code)

Max Activating Token Index: 128

Text #14

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.0542. Min Act: -0.0003

Data Index: 695663 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 11.7493. Min Range: -11.7493

Max Act: 10.9631. Min Act: -0.0003

Data Index: 1523476 (Python Code)

Max Activating Token Index: 601

Text #16

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.0330. Min Act: -0.0002

Data Index: 1616048 (Python Code)

Max Activating Token Index: 341

Text #17

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.0285. Min Act: -0.0003

Data Index: 1423071 (Python Code)

Max Activating Token Index: 214

Text #18

Max Range: 11.7493. Min Range: -11.7493

Max Act: 11.0255. Min Act: -0.0003

Data Index: 1622322 (Python Code)

Max Activating Token Index: 239

Text #19

Max Range: 11.7493. Min Range: -11.7493

Max Act: 10.9318. Min Act: -0.0002

Data Index: 1515159 (Python Code)

Max Activating Token Index: 261