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

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

Neuron 1662 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7789. Min Range: -5.7789

Max Act: 5.7789. Min Act: 0.0000

Data Index: 1572153 (Python Code)

Max Activating Token Index: 940

Text #1

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.7163. Min Act: -0.0000

Data Index: 1493906 (Python Code)

Max Activating Token Index: 223

Text #2

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.6361. Min Act: -0.0000

Data Index: 1596199 (Python Code)

Max Activating Token Index: 437

Text #3

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.4991. Min Act: 0.0000

Data Index: 1651367 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.7612. Min Act: -0.0000

Data Index: 1534166 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 5.7789. Min Range: -5.7789

Max Act: 3.7979. Min Act: -0.0000

Data Index: 1546869 (Python Code)

Max Activating Token Index: 306

Text #6

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.4950. Min Act: -0.0000

Data Index: 1438357 (Python Code)

Max Activating Token Index: 568

Text #7

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.2127. Min Act: -0.0000

Data Index: 1408768 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.3739. Min Act: -0.0000

Data Index: 1605442 (Python Code)

Max Activating Token Index: 231

Text #9

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.3085. Min Act: -0.0000

Data Index: 1569273 (Python Code)

Max Activating Token Index: 417

Text #10

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.3177. Min Act: -0.0000

Data Index: 1540765 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 5.7789. Min Range: -5.7789

Max Act: 3.6395. Min Act: -0.0000

Data Index: 1366521 (Python Code)

Max Activating Token Index: 411

Text #12

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.0358. Min Act: -0.0000

Data Index: 1395708 (Python Code)

Max Activating Token Index: 518

Text #13

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.0123. Min Act: 0.0000

Data Index: 1656148 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.3344. Min Act: -0.0000

Data Index: 1521162 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.1506. Min Act: -0.0000

Data Index: 1476777 (Python Code)

Max Activating Token Index: 435

Text #16

Max Range: 5.7789. Min Range: -5.7789

Max Act: 3.8657. Min Act: -0.0000

Data Index: 1459260 (Python Code)

Max Activating Token Index: 668

Text #17

Max Range: 5.7789. Min Range: -5.7789

Max Act: 4.0569. Min Act: -0.0000

Data Index: 1568958 (Python Code)

Max Activating Token Index: 234

Text #18

Max Range: 5.7789. Min Range: -5.7789

Max Act: 3.5189. Min Act: -0.0000

Data Index: 1459677 (Python Code)

Max Activating Token Index: 773

Text #19

Max Range: 5.7789. Min Range: -5.7789

Max Act: 3.9940. Min Act: -0.0000

Data Index: 1460721 (Python Code)

Max Activating Token Index: 410