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

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

Neuron 155 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: 3.8382. Min Range: -3.8382

Max Act: 3.8382. Min Act: -0.1700

Data Index: 1304096 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.8070. Min Act: -0.1700

Data Index: 127745 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.7757. Min Act: -0.1700

Data Index: 617131 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.7757. Min Act: -0.1700

Data Index: 1038526 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.8070. Min Act: -0.1700

Data Index: 601392 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.7444. Min Act: -0.1700

Data Index: 960226 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.7444. Min Act: -0.1700

Data Index: 494155 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.7131. Min Act: -0.1700

Data Index: 330086 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.7444. Min Act: -0.1700

Data Index: 384130 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.7444. Min Act: -0.1700

Data Index: 823627 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.7444. Min Act: -0.1700

Data Index: 843695 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.7131. Min Act: -0.1700

Data Index: 217035 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.6818. Min Act: -0.1700

Data Index: 975171 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.6818. Min Act: -0.1700

Data Index: 1315689 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.6818. Min Act: -0.1700

Data Index: 307845 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.6818. Min Act: -0.1700

Data Index: 118637 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.6505. Min Act: -0.1700

Data Index: 188056 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.6505. Min Act: -0.1700

Data Index: 35364 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.6818. Min Act: -0.1700

Data Index: 550266 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 3.8382. Min Range: -3.8382

Max Act: 3.6192. Min Act: -0.1700

Data Index: 223146 (C4 (Web Text))

Max Activating Token Index: 162