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

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

Neuron 333 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: 3.8749. Min Range: -3.8749

Max Act: 3.8749. Min Act: -0.1700

Data Index: 1548485 (Python Code)

Max Activating Token Index: 629

Text #1

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.8465. Min Act: -0.1700

Data Index: 1396630 (Python Code)

Max Activating Token Index: 843

Text #2

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.8256. Min Act: -0.1700

Data Index: 1631600 (Python Code)

Max Activating Token Index: 54

Text #3

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.8101. Min Act: -0.1700

Data Index: 1583903 (Python Code)

Max Activating Token Index: 306

Text #4

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.7730. Min Act: -0.1700

Data Index: 1441838 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.7812. Min Act: -0.1700

Data Index: 1551040 (Python Code)

Max Activating Token Index: 359

Text #6

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.7669. Min Act: -0.1700

Data Index: 1630182 (Python Code)

Max Activating Token Index: 453

Text #7

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.7584. Min Act: -0.1700

Data Index: 1525741 (Python Code)

Max Activating Token Index: 591

Text #8

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.7602. Min Act: -0.1700

Data Index: 1394581 (Python Code)

Max Activating Token Index: 242

Text #9

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.7284. Min Act: -0.1700

Data Index: 1399472 (Python Code)

Max Activating Token Index: 889

Text #10

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.6946. Min Act: -0.1700

Data Index: 1624001 (Python Code)

Max Activating Token Index: 586

Text #11

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.6936. Min Act: -0.1700

Data Index: 1396536 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.7309. Min Act: -0.1700

Data Index: 1398377 (Python Code)

Max Activating Token Index: 758

Text #13

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.6974. Min Act: -0.1700

Data Index: 1375861 (Python Code)

Max Activating Token Index: 891

Text #14

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.7248. Min Act: -0.1700

Data Index: 1525194 (Python Code)

Max Activating Token Index: 597

Text #15

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.7206. Min Act: -0.1700

Data Index: 1544362 (Python Code)

Max Activating Token Index: 222

Text #16

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.7072. Min Act: -0.1700

Data Index: 1417707 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.6833. Min Act: -0.1700

Data Index: 1546256 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.6673. Min Act: -0.1700

Data Index: 1491711 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 3.8749. Min Range: -3.8749

Max Act: 3.6951. Min Act: -0.1700

Data Index: 1494165 (Python Code)

Max Activating Token Index: 979