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

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

Neuron 1700 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: 3.4456. Min Range: -3.4456

Max Act: 3.4456. Min Act: -0.1700

Data Index: 676705 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.4456. Min Act: -0.1700

Data Index: 194699 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.4456. Min Act: -0.1700

Data Index: 188902 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.4299. Min Act: -0.1700

Data Index: 297555 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.3357. Min Act: -0.1700

Data Index: 418757 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.3671. Min Act: -0.1700

Data Index: 592762 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.3671. Min Act: -0.1700

Data Index: 4702 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.3671. Min Act: -0.1700

Data Index: 644326 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.3043. Min Act: -0.1700

Data Index: 789930 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.3514. Min Act: -0.1700

Data Index: 969401 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.2415. Min Act: -0.1700

Data Index: 905180 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.2572. Min Act: -0.1700

Data Index: 252657 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.2886. Min Act: -0.1700

Data Index: 307683 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.2415. Min Act: -0.1700

Data Index: 55349 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.2415. Min Act: -0.1700

Data Index: 1244999 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.2415. Min Act: -0.1700

Data Index: 843887 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.2100. Min Act: -0.1700

Data Index: 487896 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.2100. Min Act: -0.1700

Data Index: 742275 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.2100. Min Act: -0.1700

Data Index: 778516 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 3.4456. Min Range: -3.4456

Max Act: 3.2258. Min Act: -0.1700

Data Index: 665812 (C4 (Web Text))

Max Activating Token Index: 759