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

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

Neuron 1531 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: 3.6386. Min Range: -3.6386

Max Act: 3.6386. Min Act: -0.1700

Data Index: 39517 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.6073. Min Act: -0.1700

Data Index: 910459 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.5133. Min Act: -0.1700

Data Index: 289920 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.5133. Min Act: -0.1700

Data Index: 807034 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.4507. Min Act: -0.1700

Data Index: 1073573 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.4507. Min Act: -0.1700

Data Index: 503060 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.4193. Min Act: -0.1700

Data Index: 607567 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.4507. Min Act: -0.1700

Data Index: 803397 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.4193. Min Act: -0.1700

Data Index: 1097847 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.4193. Min Act: -0.1700

Data Index: 551048 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.4193. Min Act: -0.1700

Data Index: 38337 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.3879. Min Act: -0.1700

Data Index: 283253 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.3879. Min Act: -0.1700

Data Index: 899852 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.3252. Min Act: -0.1700

Data Index: 1090651 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.3566. Min Act: -0.1700

Data Index: 41290 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.3879. Min Act: -0.1700

Data Index: 1126276 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.3879. Min Act: -0.1700

Data Index: 436532 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.4193. Min Act: -0.1700

Data Index: 193556 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.3879. Min Act: -0.1700

Data Index: 1307151 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 3.6386. Min Range: -3.6386

Max Act: 3.3879. Min Act: -0.1700

Data Index: 1347447 (C4 (Web Text))

Max Activating Token Index: 678