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

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

Neuron 1377 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.6337. Min Act: -0.1700

Data Index: 756147 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.3525. Min Act: -0.1700

Data Index: 188532 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.2275. Min Act: -0.1700

Data Index: 540472 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.2275. Min Act: -0.1700

Data Index: 964538 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1962. Min Act: -0.1700

Data Index: 521407 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.2587. Min Act: -0.1700

Data Index: 292079 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1962. Min Act: -0.1700

Data Index: 100920 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1650. Min Act: -0.1700

Data Index: 398492 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1025. Min Act: -0.1700

Data Index: 1111380 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1650. Min Act: -0.1700

Data Index: 848803 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1337. Min Act: -0.1700

Data Index: 524944 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1025. Min Act: -0.1700

Data Index: 346859 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1650. Min Act: -0.1700

Data Index: 599566 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1337. Min Act: -0.1700

Data Index: 598176 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1962. Min Act: -0.1700

Data Index: 1221788 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1337. Min Act: -0.1700

Data Index: 1162195 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1650. Min Act: -0.1700

Data Index: 323570 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1337. Min Act: -0.1700

Data Index: 261459 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1025. Min Act: -0.1700

Data Index: 469220 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 5.6337. Min Range: -5.6337

Max Act: 5.1650. Min Act: -0.1700

Data Index: 211498 (C4 (Web Text))

Max Activating Token Index: 209