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

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

Neuron 127 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: 3.6023. Min Range: -3.6023

Max Act: 3.6023. Min Act: -0.1700

Data Index: 1571161 (Python Code)

Max Activating Token Index: 391

Text #1

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4164. Min Act: -0.1700

Data Index: 1373974 (Python Code)

Max Activating Token Index: 128

Text #2

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4126. Min Act: -0.1700

Data Index: 1638371 (Python Code)

Max Activating Token Index: 737

Text #3

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4082. Min Act: -0.1700

Data Index: 1388387 (Python Code)

Max Activating Token Index: 603

Text #4

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3659. Min Act: -0.1700

Data Index: 1586996 (Python Code)

Max Activating Token Index: 782

Text #5

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3968. Min Act: -0.1700

Data Index: 1602516 (Python Code)

Max Activating Token Index: 491

Text #6

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3834. Min Act: -0.1700

Data Index: 1640950 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3882. Min Act: -0.1700

Data Index: 1540608 (Python Code)

Max Activating Token Index: 334

Text #8

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3894. Min Act: -0.1700

Data Index: 1531231 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4190. Min Act: -0.1700

Data Index: 1481687 (Python Code)

Max Activating Token Index: 389

Text #10

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3894. Min Act: -0.1700

Data Index: 1586180 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3769. Min Act: -0.1700

Data Index: 1430312 (Python Code)

Max Activating Token Index: 18

Text #12

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3836. Min Act: -0.1700

Data Index: 1510748 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3565. Min Act: -0.1700

Data Index: 1364970 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3696. Min Act: -0.1700

Data Index: 1517363 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3518. Min Act: -0.1700

Data Index: 1410236 (Python Code)

Max Activating Token Index: 390

Text #16

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3300. Min Act: -0.1700

Data Index: 1567522 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3305. Min Act: -0.1700

Data Index: 1367195 (Python Code)

Max Activating Token Index: 222

Text #18

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3078. Min Act: -0.1700

Data Index: 1571319 (Python Code)

Max Activating Token Index: 430

Text #19

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3420. Min Act: -0.1700

Data Index: 1490193 (Python Code)

Max Activating Token Index: 4