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

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

Neuron 1611 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.7205. Min Act: -0.0000

Data Index: 1536112 (Python Code)

Max Activating Token Index: 705

Text #1

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.8320. Min Act: -0.0000

Data Index: 1619427 (Python Code)

Max Activating Token Index: 377

Text #2

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.6499. Min Act: -0.0000

Data Index: 1515119 (Python Code)

Max Activating Token Index: 910

Text #3

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.5830. Min Act: -0.0000

Data Index: 1537112 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.7247. Min Act: -0.0000

Data Index: 1474944 (Python Code)

Max Activating Token Index: 436

Text #5

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.5869. Min Act: -0.0000

Data Index: 1616098 (Python Code)

Max Activating Token Index: 169

Text #6

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.5427. Min Act: -0.0000

Data Index: 1521919 (Python Code)

Max Activating Token Index: 233

Text #7

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.6324. Min Act: -0.0000

Data Index: 1506944 (Python Code)

Max Activating Token Index: 428

Text #8

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.4219. Min Act: -0.0000

Data Index: 1517301 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.4469. Min Act: -0.0000

Data Index: 1591613 (Python Code)

Max Activating Token Index: 348

Text #10

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.1951. Min Act: -0.0000

Data Index: 1409489 (Python Code)

Max Activating Token Index: 219

Text #11

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.1481. Min Act: -0.0000

Data Index: 1570072 (Python Code)

Max Activating Token Index: 117

Text #12

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.1913. Min Act: -0.0000

Data Index: 772668 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.1822. Min Act: -0.0000

Data Index: 1585177 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.1491. Min Act: -0.0000

Data Index: 1472264 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.1398. Min Act: -0.0000

Data Index: 1593179 (Python Code)

Max Activating Token Index: 496

Text #16

Max Range: 3.7205. Min Range: -3.7205

Max Act: 1.9878. Min Act: -0.0000

Data Index: 1626968 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.0669. Min Act: -0.0000

Data Index: 1612272 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 3.7205. Min Range: -3.7205

Max Act: 1.9425. Min Act: -0.0000

Data Index: 1519444 (Python Code)

Max Activating Token Index: 158

Text #19

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.0448. Min Act: -0.0000

Data Index: 1609019 (Python Code)

Max Activating Token Index: 83