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

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

Neuron 436 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: 3.5415. Min Range: -3.5415

Max Act: 3.5415. Min Act: -0.1700

Data Index: 1182255 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.4475. Min Act: -0.1700

Data Index: 110722 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.3848. Min Act: -0.1700

Data Index: 661457 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.4162. Min Act: -0.1700

Data Index: 977127 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.4162. Min Act: -0.1700

Data Index: 658852 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.4162. Min Act: -0.1700

Data Index: 439171 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.3063. Min Act: -0.1700

Data Index: 766832 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.3377. Min Act: -0.1700

Data Index: 1122462 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.3534. Min Act: -0.1700

Data Index: 284834 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.3848. Min Act: -0.1700

Data Index: 653755 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.3377. Min Act: -0.1700

Data Index: 628069 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.3220. Min Act: -0.1700

Data Index: 976124 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.3534. Min Act: -0.1700

Data Index: 1155356 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.2906. Min Act: -0.1700

Data Index: 1047292 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.3377. Min Act: -0.1700

Data Index: 194194 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.2906. Min Act: -0.1700

Data Index: 140802 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.2749. Min Act: -0.1700

Data Index: 1281680 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.2592. Min Act: -0.1700

Data Index: 919064 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.2592. Min Act: -0.1700

Data Index: 692402 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 3.5415. Min Range: -3.5415

Max Act: 3.2592. Min Act: -0.1700

Data Index: 704039 (C4 (Web Text))

Max Activating Token Index: 651