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

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

Neuron 96 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.5662. Min Act: -0.0000

Data Index: 1544273 (Python Code)

Max Activating Token Index: 763

Text #1

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.6384. Min Act: -0.0000

Data Index: 1424190 (Python Code)

Max Activating Token Index: 273

Text #2

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.6315. Min Act: -0.0000

Data Index: 1367299 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.2152. Min Act: -0.0001

Data Index: 1602151 (Python Code)

Max Activating Token Index: 365

Text #4

Max Range: 1.6384. Min Range: -1.6384

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1367618 (Python Code)

Max Activating Token Index: 794

Text #5

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.2735. Min Act: -0.0001

Data Index: 1499479 (Python Code)

Max Activating Token Index: 85

Text #6

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.2029. Min Act: -0.0000

Data Index: 1577728 (Python Code)

Max Activating Token Index: 849

Text #7

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.1481. Min Act: -0.0001

Data Index: 1436462 (Python Code)

Max Activating Token Index: 444

Text #8

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1619694 (Python Code)

Max Activating Token Index: 286

Text #9

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.2054. Min Act: -0.0001

Data Index: 343125 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 1.6384. Min Range: -1.6384

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1538832 (Python Code)

Max Activating Token Index: 774

Text #11

Max Range: 1.6384. Min Range: -1.6384

Max Act: 0.8281. Min Act: -0.0000

Data Index: 1588244 (Python Code)

Max Activating Token Index: 749

Text #12

Max Range: 1.6384. Min Range: -1.6384

Max Act: 0.9276. Min Act: -0.0001

Data Index: 1403471 (Python Code)

Max Activating Token Index: 251

Text #13

Max Range: 1.6384. Min Range: -1.6384

Max Act: 0.8935. Min Act: -0.0001

Data Index: 1558321 (Python Code)

Max Activating Token Index: 245

Text #14

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.0533. Min Act: -0.0000

Data Index: 1615119 (Python Code)

Max Activating Token Index: 735

Text #15

Max Range: 1.6384. Min Range: -1.6384

Max Act: 0.9281. Min Act: -0.0001

Data Index: 222135 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 1.6384. Min Range: -1.6384

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1562052 (Python Code)

Max Activating Token Index: 964

Text #17

Max Range: 1.6384. Min Range: -1.6384

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1535383 (Python Code)

Max Activating Token Index: 373

Text #18

Max Range: 1.6384. Min Range: -1.6384

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1491486 (Python Code)

Max Activating Token Index: 720

Text #19

Max Range: 1.6384. Min Range: -1.6384

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1361371 (Python Code)

Max Activating Token Index: 24