Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1797 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2377. Min Range: -5.2377

Max Act: 5.2377. Min Act: -0.1700

Data Index: 807370 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 5.2377. Min Range: -5.2377

Max Act: 5.0502. Min Act: -0.1700

Data Index: 825809 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.9877. Min Act: -0.1700

Data Index: 484095 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 5.2377. Min Range: -5.2377

Max Act: 5.0190. Min Act: -0.1700

Data Index: 1281212 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 5.2377. Min Range: -5.2377

Max Act: 5.0190. Min Act: -0.1700

Data Index: 637316 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8627. Min Act: -0.1700

Data Index: 123490 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8002. Min Act: -0.1700

Data Index: 948259 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 5.2377. Min Range: -5.2377

Max Act: 5.0190. Min Act: -0.1700

Data Index: 785927 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.9252. Min Act: -0.1700

Data Index: 668322 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8940. Min Act: -0.1700

Data Index: 426189 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.9565. Min Act: -0.1700

Data Index: 622637 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8315. Min Act: -0.1700

Data Index: 1020789 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8940. Min Act: -0.1700

Data Index: 608822 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8627. Min Act: -0.1700

Data Index: 411265 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8627. Min Act: -0.1700

Data Index: 1160810 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8315. Min Act: -0.1700

Data Index: 716147 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8940. Min Act: -0.1700

Data Index: 286642 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8002. Min Act: -0.1700

Data Index: 7141 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8315. Min Act: -0.1700

Data Index: 1092935 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 5.2377. Min Range: -5.2377

Max Act: 4.8002. Min Act: -0.1700

Data Index: 239588 (C4 (Web Text))

Max Activating Token Index: 542