Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 355 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.4665. Min Act: -0.1700

Data Index: 1384403 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.3817. Min Act: -0.1700

Data Index: 1430080 (Python Code)

Max Activating Token Index: 720

Text #2

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.3607. Min Act: -0.1700

Data Index: 1450712 (Python Code)

Max Activating Token Index: 557

Text #3

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.3313. Min Act: -0.1700

Data Index: 1441966 (Python Code)

Max Activating Token Index: 231

Text #4

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.3133. Min Act: -0.1700

Data Index: 1628326 (Python Code)

Max Activating Token Index: 600

Text #5

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.3061. Min Act: -0.1700

Data Index: 1527726 (Python Code)

Max Activating Token Index: 1011

Text #6

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.3216. Min Act: -0.1700

Data Index: 1446849 (Python Code)

Max Activating Token Index: 773

Text #7

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.2918. Min Act: -0.1700

Data Index: 1535181 (Python Code)

Max Activating Token Index: 543

Text #8

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.2878. Min Act: -0.1700

Data Index: 1612394 (Python Code)

Max Activating Token Index: 994

Text #9

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.2405. Min Act: -0.1700

Data Index: 1387679 (Python Code)

Max Activating Token Index: 1013

Text #10

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.2082. Min Act: -0.1700

Data Index: 1372089 (Python Code)

Max Activating Token Index: 896

Text #11

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.2379. Min Act: -0.1700

Data Index: 1606549 (Python Code)

Max Activating Token Index: 325

Text #12

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.2382. Min Act: -0.1700

Data Index: 1599947 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.2153. Min Act: -0.1700

Data Index: 1558265 (Python Code)

Max Activating Token Index: 409

Text #14

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.1906. Min Act: -0.1700

Data Index: 1505958 (Python Code)

Max Activating Token Index: 149

Text #15

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.1714. Min Act: -0.1700

Data Index: 1389655 (Python Code)

Max Activating Token Index: 501

Text #16

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.2320. Min Act: -0.1700

Data Index: 1528102 (Python Code)

Max Activating Token Index: 917

Text #17

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.2083. Min Act: -0.1700

Data Index: 1492586 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.2231. Min Act: -0.1700

Data Index: 1475648 (Python Code)

Max Activating Token Index: 851

Text #19

Max Range: 6.4665. Min Range: -6.4665

Max Act: 6.1739. Min Act: -0.1700

Data Index: 1477311 (Python Code)

Max Activating Token Index: 884