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

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

Neuron 3588 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.5316. Min Act: -0.0000

Data Index: 1386875 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.4933. Min Act: -0.0000

Data Index: 1435944 (Python Code)

Max Activating Token Index: 328

Text #2

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.2913. Min Act: -0.0000

Data Index: 1419192 (Python Code)

Max Activating Token Index: 424

Text #3

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.5303. Min Act: -0.0000

Data Index: 1435696 (Python Code)

Max Activating Token Index: 279

Text #4

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.3581. Min Act: -0.0000

Data Index: 1604010 (Python Code)

Max Activating Token Index: 363

Text #5

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.3064. Min Act: -0.0000

Data Index: 1520253 (Python Code)

Max Activating Token Index: 198

Text #6

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.1199. Min Act: -0.0000

Data Index: 1462113 (Python Code)

Max Activating Token Index: 148

Text #7

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.3146. Min Act: -0.0000

Data Index: 1418866 (Python Code)

Max Activating Token Index: 571

Text #8

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.2913. Min Act: -0.0000

Data Index: 1505102 (Python Code)

Max Activating Token Index: 366

Text #9

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.2652. Min Act: -0.0000

Data Index: 1460275 (Python Code)

Max Activating Token Index: 493

Text #10

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.0357. Min Act: -0.0000

Data Index: 1389959 (Python Code)

Max Activating Token Index: 410

Text #11

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.3834. Min Act: -0.0000

Data Index: 1588860 (Python Code)

Max Activating Token Index: 883

Text #12

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.3216. Min Act: -0.0000

Data Index: 1406299 (Python Code)

Max Activating Token Index: 785

Text #13

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.2206. Min Act: -0.0000

Data Index: 1553006 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.3234. Min Act: -0.0000

Data Index: 1392895 (Python Code)

Max Activating Token Index: 438

Text #15

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.1227. Min Act: -0.0000

Data Index: 1501485 (Python Code)

Max Activating Token Index: 171

Text #16

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.2300. Min Act: 0.0000

Data Index: 1479890 (Python Code)

Max Activating Token Index: 554

Text #17

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.2261. Min Act: -0.0000

Data Index: 1400099 (Python Code)

Max Activating Token Index: 264

Text #18

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.1024. Min Act: -0.0000

Data Index: 1369977 (Python Code)

Max Activating Token Index: 92

Text #19

Max Range: 2.5316. Min Range: -2.5316

Max Act: 2.3001. Min Act: -0.0000

Data Index: 1457422 (Python Code)

Max Activating Token Index: 953