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

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

Neuron 173 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.5421. Min Act: -0.0001

Data Index: 1400637 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.4756. Min Act: -0.0000

Data Index: 1494720 (Python Code)

Max Activating Token Index: 308

Text #2

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.3258. Min Act: -0.0000

Data Index: 1431888 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.3623. Min Act: -0.0000

Data Index: 1600378 (Python Code)

Max Activating Token Index: 143

Text #4

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.2592. Min Act: -0.0000

Data Index: 1610676 (Python Code)

Max Activating Token Index: 369

Text #5

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.2371. Min Act: -0.0000

Data Index: 1648696 (Python Code)

Max Activating Token Index: 482

Text #6

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.3351. Min Act: -0.0000

Data Index: 1644187 (Python Code)

Max Activating Token Index: 589

Text #7

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.1281. Min Act: -0.0000

Data Index: 1363349 (Python Code)

Max Activating Token Index: 179

Text #8

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.2340. Min Act: -0.0000

Data Index: 1639952 (Python Code)

Max Activating Token Index: 951

Text #9

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.0645. Min Act: -0.0000

Data Index: 48183 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.0834. Min Act: -0.0000

Data Index: 1512442 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 2.5421. Min Range: -2.5421

Max Act: 1.8205. Min Act: -0.0000

Data Index: 1406793 (Python Code)

Max Activating Token Index: 165

Text #12

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.1293. Min Act: -0.0000

Data Index: 1609837 (Python Code)

Max Activating Token Index: 866

Text #13

Max Range: 2.5421. Min Range: -2.5421

Max Act: 2.0204. Min Act: -0.0000

Data Index: 1372772 (Python Code)

Max Activating Token Index: 913

Text #14

Max Range: 2.5421. Min Range: -2.5421

Max Act: 1.9735. Min Act: -0.0000

Data Index: 1463541 (Python Code)

Max Activating Token Index: 897

Text #15

Max Range: 2.5421. Min Range: -2.5421

Max Act: 1.9288. Min Act: -0.0000

Data Index: 1567288 (Python Code)

Max Activating Token Index: 698

Text #16

Max Range: 2.5421. Min Range: -2.5421

Max Act: 1.8535. Min Act: -0.0000

Data Index: 1571203 (Python Code)

Max Activating Token Index: 556

Text #17

Max Range: 2.5421. Min Range: -2.5421

Max Act: 1.8459. Min Act: -0.0000

Data Index: 1375442 (Python Code)

Max Activating Token Index: 294

Text #18

Max Range: 2.5421. Min Range: -2.5421

Max Act: 1.9060. Min Act: -0.0000

Data Index: 1462608 (Python Code)

Max Activating Token Index: 173

Text #19

Max Range: 2.5421. Min Range: -2.5421

Max Act: 1.7835. Min Act: -0.0000

Data Index: 1466969 (Python Code)

Max Activating Token Index: 433