Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 17 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0448. Min Range: -5.0448

Max Act: 5.0448. Min Act: -0.1700

Data Index: 1479339 (Python Code)

Max Activating Token Index: 799

Text #1

Max Range: 5.0448. Min Range: -5.0448

Max Act: 5.0448. Min Act: -0.1700

Data Index: 1576115 (Python Code)

Max Activating Token Index: 661

Text #2

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.9823. Min Act: -0.1700

Data Index: 1641729 (Python Code)

Max Activating Token Index: 868

Text #3

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.9510. Min Act: -0.1700

Data Index: 1596689 (Python Code)

Max Activating Token Index: 423

Text #4

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.7948. Min Act: -0.1700

Data Index: 1403332 (Python Code)

Max Activating Token Index: 698

Text #5

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.8260. Min Act: -0.1700

Data Index: 1421521 (Python Code)

Max Activating Token Index: 545

Text #6

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.7948. Min Act: -0.1700

Data Index: 1509563 (Python Code)

Max Activating Token Index: 822

Text #7

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.7948. Min Act: -0.1700

Data Index: 1515223 (Python Code)

Max Activating Token Index: 586

Text #8

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.7323. Min Act: -0.1700

Data Index: 1644238 (Python Code)

Max Activating Token Index: 828

Text #9

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.7635. Min Act: -0.1700

Data Index: 1366603 (Python Code)

Max Activating Token Index: 538

Text #10

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.7323. Min Act: -0.1700

Data Index: 1467161 (Python Code)

Max Activating Token Index: 153

Text #11

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.6385. Min Act: -0.1700

Data Index: 1380037 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.6698. Min Act: -0.1700

Data Index: 1511384 (Python Code)

Max Activating Token Index: 590

Text #13

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.6385. Min Act: -0.1700

Data Index: 1478068 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.6698. Min Act: -0.1700

Data Index: 1512566 (Python Code)

Max Activating Token Index: 340

Text #15

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.6073. Min Act: -0.1700

Data Index: 1541169 (Python Code)

Max Activating Token Index: 476

Text #16

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.6698. Min Act: -0.1700

Data Index: 1614241 (Python Code)

Max Activating Token Index: 877

Text #17

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.6385. Min Act: -0.1700

Data Index: 1591227 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.6073. Min Act: -0.1700

Data Index: 1470746 (Python Code)

Max Activating Token Index: 112

Text #19

Max Range: 5.0448. Min Range: -5.0448

Max Act: 4.6073. Min Act: -0.1700

Data Index: 1494196 (Python Code)

Max Activating Token Index: 661