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

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

Neuron 1253 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: 1.8371. Min Range: -1.8371

Max Act: 1.8371. Min Act: -0.0000

Data Index: 1653436 (Python Code)

Max Activating Token Index: 191

Text #1

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1451089 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.4154. Min Act: -0.0000

Data Index: 1443568 (Python Code)

Max Activating Token Index: 540

Text #3

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1365581 (Python Code)

Max Activating Token Index: 245

Text #4

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.2167. Min Act: -0.0000

Data Index: 1475159 (Python Code)

Max Activating Token Index: 426

Text #5

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1471962 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1566781 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1442000 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.2517. Min Act: -0.0000

Data Index: 1473064 (Python Code)

Max Activating Token Index: 395

Text #9

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1597554 (Python Code)

Max Activating Token Index: 901

Text #10

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.2913. Min Act: -0.0000

Data Index: 1546341 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.2847. Min Act: -0.0000

Data Index: 1629551 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.1991. Min Act: -0.0000

Data Index: 1556763 (Python Code)

Max Activating Token Index: 488

Text #13

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1624034 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.1930. Min Act: -0.0000

Data Index: 1401467 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.1073. Min Act: -0.0000

Data Index: 1398904 (Python Code)

Max Activating Token Index: 728

Text #16

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.1697. Min Act: -0.0000

Data Index: 1580843 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.1632. Min Act: -0.0000

Data Index: 1592207 (Python Code)

Max Activating Token Index: 604

Text #18

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1532894 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 1.8371. Min Range: -1.8371

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1590439 (Python Code)

Max Activating Token Index: 619