Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 136 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.9503. Min Act: -0.1700

Data Index: 1363243 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.9190. Min Act: -0.1700

Data Index: 1505930 (Python Code)

Max Activating Token Index: 181

Text #2

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.7939. Min Act: -0.1700

Data Index: 1439923 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.7939. Min Act: -0.1700

Data Index: 1540442 (Python Code)

Max Activating Token Index: 555

Text #4

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.7626. Min Act: -0.1700

Data Index: 1370151 (Python Code)

Max Activating Token Index: 419

Text #5

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.7470. Min Act: -0.1700

Data Index: 1367582 (Python Code)

Max Activating Token Index: 809

Text #6

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.6844. Min Act: -0.1700

Data Index: 1472046 (Python Code)

Max Activating Token Index: 582

Text #7

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.7157. Min Act: -0.1700

Data Index: 1367010 (Python Code)

Max Activating Token Index: 603

Text #8

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.7157. Min Act: -0.1700

Data Index: 1555752 (Python Code)

Max Activating Token Index: 386

Text #9

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.6687. Min Act: -0.1700

Data Index: 1458656 (Python Code)

Max Activating Token Index: 590

Text #10

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.6844. Min Act: -0.1700

Data Index: 1628997 (Python Code)

Max Activating Token Index: 590

Text #11

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.6687. Min Act: -0.1700

Data Index: 1492824 (Python Code)

Max Activating Token Index: 400

Text #12

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.6687. Min Act: -0.1700

Data Index: 1514693 (Python Code)

Max Activating Token Index: 147

Text #13

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.6374. Min Act: -0.1700

Data Index: 1551926 (Python Code)

Max Activating Token Index: 282

Text #14

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.6531. Min Act: -0.1700

Data Index: 1481917 (Python Code)

Max Activating Token Index: 577

Text #15

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.6374. Min Act: -0.1700

Data Index: 1625937 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.5905. Min Act: -0.1700

Data Index: 1581912 (Python Code)

Max Activating Token Index: 891

Text #17

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.5905. Min Act: -0.1700

Data Index: 1565109 (Python Code)

Max Activating Token Index: 36

Text #18

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.5591. Min Act: -0.1700

Data Index: 1393379 (Python Code)

Max Activating Token Index: 594

Text #19

Max Range: 3.9503. Min Range: -3.9503

Max Act: 3.5122. Min Act: -0.1700

Data Index: 1491077 (Python Code)

Max Activating Token Index: 358