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

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

Neuron 628 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: 3.5388. Min Range: -3.5388

Max Act: 3.5232. Min Act: -0.1700

Data Index: 1148370 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.5388. Min Act: -0.1700

Data Index: 186831 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4918. Min Act: -0.1700

Data Index: 122139 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.5075. Min Act: -0.1700

Data Index: 983434 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4918. Min Act: -0.1700

Data Index: 700257 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.5075. Min Act: -0.1700

Data Index: 214384 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4918. Min Act: -0.1700

Data Index: 774987 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4761. Min Act: -0.1700

Data Index: 1311525 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4448. Min Act: -0.1700

Data Index: 571349 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4605. Min Act: -0.1700

Data Index: 1136810 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4448. Min Act: -0.1700

Data Index: 275591 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4291. Min Act: -0.1700

Data Index: 657957 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4291. Min Act: -0.1700

Data Index: 824584 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4134. Min Act: -0.1700

Data Index: 731538 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4448. Min Act: -0.1700

Data Index: 240320 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4448. Min Act: -0.1700

Data Index: 299988 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4134. Min Act: -0.1700

Data Index: 401953 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4291. Min Act: -0.1700

Data Index: 390134 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4134. Min Act: -0.1700

Data Index: 1167935 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 3.5388. Min Range: -3.5388

Max Act: 3.4448. Min Act: -0.1700

Data Index: 22127 (C4 (Web Text))

Max Activating Token Index: 637