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

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

Neuron 2196 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: 1.6887. Min Range: -1.6887

Max Act: 1.6887. Min Act: -0.0000

Data Index: 1404351 (Python Code)

Max Activating Token Index: 302

Text #1

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.5866. Min Act: -0.0000

Data Index: 1447339 (Python Code)

Max Activating Token Index: 725

Text #2

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.6143. Min Act: -0.0000

Data Index: 1448458 (Python Code)

Max Activating Token Index: 820

Text #3

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.5367. Min Act: -0.0000

Data Index: 1369356 (Python Code)

Max Activating Token Index: 916

Text #4

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.5540. Min Act: -0.0000

Data Index: 1612522 (Python Code)

Max Activating Token Index: 926

Text #5

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.3875. Min Act: -0.0000

Data Index: 1642842 (Python Code)

Max Activating Token Index: 72

Text #6

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.5527. Min Act: -0.0000

Data Index: 1526147 (Python Code)

Max Activating Token Index: 864

Text #7

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.3294. Min Act: -0.0000

Data Index: 1432389 (Python Code)

Max Activating Token Index: 888

Text #8

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.5024. Min Act: -0.0000

Data Index: 1536439 (Python Code)

Max Activating Token Index: 937

Text #9

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.4999. Min Act: -0.0000

Data Index: 1561899 (Python Code)

Max Activating Token Index: 864

Text #10

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.2706. Min Act: -0.0000

Data Index: 1625246 (Python Code)

Max Activating Token Index: 507

Text #11

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1377421 (Python Code)

Max Activating Token Index: 699

Text #12

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1419625 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.2409. Min Act: -0.0000

Data Index: 1372664 (Python Code)

Max Activating Token Index: 749

Text #14

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.1392. Min Act: -0.0000

Data Index: 1562807 (Python Code)

Max Activating Token Index: 77

Text #15

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1597668 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.2268. Min Act: -0.0000

Data Index: 1560199 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.2532. Min Act: -0.0000

Data Index: 1465757 (Python Code)

Max Activating Token Index: 770

Text #18

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.1353. Min Act: -0.0000

Data Index: 1558900 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 1.6887. Min Range: -1.6887

Max Act: 1.2365. Min Act: -0.0000

Data Index: 1447099 (Python Code)

Max Activating Token Index: 845