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

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

Neuron 1541 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: 1.2131. Min Range: -1.2131

Max Act: 1.2131. Min Act: -0.0000

Data Index: 1458971 (Python Code)

Max Activating Token Index: 94

Text #1

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1345447 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1524948 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1618584 (Python Code)

Max Activating Token Index: 900

Text #4

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1599965 (Python Code)

Max Activating Token Index: 952

Text #5

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1540028 (Python Code)

Max Activating Token Index: 900

Text #6

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1459068 (Python Code)

Max Activating Token Index: 121

Text #7

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1397518 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8969. Min Act: -0.0000

Data Index: 1433268 (Python Code)

Max Activating Token Index: 930

Text #9

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1603136 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1506356 (Python Code)

Max Activating Token Index: 212

Text #11

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8860. Min Act: -0.0000

Data Index: 1461054 (Python Code)

Max Activating Token Index: 421

Text #12

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8404. Min Act: -0.0000

Data Index: 528241 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1036854 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1458506 (Python Code)

Max Activating Token Index: 83

Text #15

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1615368 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1493145 (Python Code)

Max Activating Token Index: 203

Text #17

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1044795 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8346. Min Act: -0.0000

Data Index: 1428905 (Python Code)

Max Activating Token Index: 123

Text #19

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.7310. Min Act: -0.0000

Data Index: 554297 (C4 (Web Text))

Max Activating Token Index: 63