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

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

Neuron 549 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.3536. Min Act: -0.1700

Data Index: 690335 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.3223. Min Act: -0.1699

Data Index: 1146072 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.2911. Min Act: -0.1699

Data Index: 487719 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.2598. Min Act: -0.1700

Data Index: 107603 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.1973. Min Act: -0.1700

Data Index: 675064 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.1973. Min Act: -0.1700

Data Index: 729372 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.2286. Min Act: -0.1700

Data Index: 44834 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.2598. Min Act: -0.1700

Data Index: 82223 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.1973. Min Act: -0.1700

Data Index: 1061582 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.2598. Min Act: -0.1700

Data Index: 1119139 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.2286. Min Act: -0.1700

Data Index: 1218735 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.2286. Min Act: -0.1700

Data Index: 404219 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.1661. Min Act: -0.1700

Data Index: 936697 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.1036. Min Act: -0.1700

Data Index: 365377 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.1036. Min Act: -0.1699

Data Index: 215676 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.1661. Min Act: -0.1699

Data Index: 857154 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.1348. Min Act: -0.1700

Data Index: 234052 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.1348. Min Act: -0.1700

Data Index: 158512 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.0723. Min Act: -0.1700

Data Index: 262507 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 5.3536. Min Range: -5.3536

Max Act: 5.1661. Min Act: -0.1699

Data Index: 993617 (C4 (Web Text))

Max Activating Token Index: 553