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

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

Neuron 508 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: 5.4427. Min Range: -5.4427

Max Act: 5.4427. Min Act: -0.1700

Data Index: 1006826 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.3489. Min Act: -0.1700

Data Index: 954317 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2864. Min Act: -0.1700

Data Index: 493472 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2864. Min Act: -0.1700

Data Index: 961381 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2864. Min Act: -0.1700

Data Index: 385167 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2552. Min Act: -0.1700

Data Index: 831162 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2864. Min Act: -0.1700

Data Index: 1132143 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.3177. Min Act: -0.1700

Data Index: 794365 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.3177. Min Act: -0.1700

Data Index: 439537 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2552. Min Act: -0.1700

Data Index: 311437 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2239. Min Act: -0.1700

Data Index: 1274218 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2552. Min Act: -0.1700

Data Index: 1331303 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2239. Min Act: -0.1700

Data Index: 366808 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2552. Min Act: -0.1700

Data Index: 609623 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2552. Min Act: -0.1700

Data Index: 246481 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2239. Min Act: -0.1700

Data Index: 222807 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2239. Min Act: -0.1700

Data Index: 415031 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.1927. Min Act: -0.1700

Data Index: 617932 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.1614. Min Act: -0.1700

Data Index: 962410 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 5.4427. Min Range: -5.4427

Max Act: 5.2239. Min Act: -0.1700

Data Index: 488555 (C4 (Web Text))

Max Activating Token Index: 963