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

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

Neuron 4110 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3508. Min Range: -4.3508

Max Act: 4.0938. Min Act: -0.0000

Data Index: 1378476 (Python Code)

Max Activating Token Index: 769

Text #1

Max Range: 4.3508. Min Range: -4.3508

Max Act: 4.3508. Min Act: -0.0000

Data Index: 1532697 (Python Code)

Max Activating Token Index: 62

Text #2

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.8968. Min Act: -0.0000

Data Index: 1387217 (Python Code)

Max Activating Token Index: 451

Text #3

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.8159. Min Act: -0.0000

Data Index: 1408945 (Python Code)

Max Activating Token Index: 402

Text #4

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.5652. Min Act: -0.0000

Data Index: 1536042 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.5413. Min Act: -0.0000

Data Index: 1410874 (Python Code)

Max Activating Token Index: 820

Text #6

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.5222. Min Act: -0.0000

Data Index: 1475183 (Python Code)

Max Activating Token Index: 655

Text #7

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.6470. Min Act: -0.0000

Data Index: 1646368 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.7095. Min Act: -0.0000

Data Index: 1485920 (Python Code)

Max Activating Token Index: 379

Text #9

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.6852. Min Act: -0.0000

Data Index: 1369516 (Python Code)

Max Activating Token Index: 590

Text #10

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.3504. Min Act: -0.0000

Data Index: 1535447 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.2382. Min Act: -0.0000

Data Index: 1489756 (Python Code)

Max Activating Token Index: 554

Text #12

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.3479. Min Act: -0.0000

Data Index: 1517701 (Python Code)

Max Activating Token Index: 350

Text #13

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.2119. Min Act: -0.0000

Data Index: 1615383 (Python Code)

Max Activating Token Index: 176

Text #14

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.3538. Min Act: -0.0000

Data Index: 1591959 (Python Code)

Max Activating Token Index: 186

Text #15

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.2130. Min Act: -0.0000

Data Index: 1602111 (Python Code)

Max Activating Token Index: 340

Text #16

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.1808. Min Act: -0.0000

Data Index: 1376417 (Python Code)

Max Activating Token Index: 493

Text #17

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.3214. Min Act: -0.0000

Data Index: 1608634 (Python Code)

Max Activating Token Index: 266

Text #18

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.1780. Min Act: -0.0000

Data Index: 1549191 (Python Code)

Max Activating Token Index: 78

Text #19

Max Range: 4.3508. Min Range: -4.3508

Max Act: 3.1585. Min Act: -0.0000

Data Index: 1582222 (Python Code)

Max Activating Token Index: 9