Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1320 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.3304. Min Act: -0.1700

Data Index: 319821 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1890. Min Act: -0.1700

Data Index: 1299232 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1417. Min Act: -0.1700

Data Index: 455779 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1260. Min Act: -0.1700

Data Index: 873164 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0945. Min Act: -0.1700

Data Index: 504904 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0945. Min Act: -0.1700

Data Index: 799770 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1102. Min Act: -0.1700

Data Index: 243368 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1417. Min Act: -0.1700

Data Index: 289240 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0787. Min Act: -0.1700

Data Index: 492958 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0787. Min Act: -0.1700

Data Index: 786963 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0629. Min Act: -0.1700

Data Index: 739056 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0629. Min Act: -0.1700

Data Index: 218015 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0471. Min Act: -0.1700

Data Index: 1263915 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0787. Min Act: -0.1700

Data Index: 152082 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0313. Min Act: -0.1700

Data Index: 1281423 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0313. Min Act: -0.1700

Data Index: 892244 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0313. Min Act: -0.1700

Data Index: 51292 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0313. Min Act: -0.1700

Data Index: 918776 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0313. Min Act: -0.1700

Data Index: 1313926 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.0155. Min Act: -0.1700

Data Index: 483371 (C4 (Web Text))

Max Activating Token Index: 647