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

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

Neuron 866 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: 3.4461. Min Range: -3.4461

Max Act: 3.4461. Min Act: -0.1700

Data Index: 581134 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.3363. Min Act: -0.1700

Data Index: 572610 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2735. Min Act: -0.1700

Data Index: 372072 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2892. Min Act: -0.1700

Data Index: 905439 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.3206. Min Act: -0.1700

Data Index: 987476 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2420. Min Act: -0.1700

Data Index: 189181 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2578. Min Act: -0.1700

Data Index: 374378 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2263. Min Act: -0.1700

Data Index: 990497 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2263. Min Act: -0.1700

Data Index: 1078567 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2106. Min Act: -0.1700

Data Index: 930802 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2106. Min Act: -0.1700

Data Index: 1078145 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2420. Min Act: -0.1700

Data Index: 933037 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2106. Min Act: -0.1700

Data Index: 294099 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2106. Min Act: -0.1700

Data Index: 682872 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2263. Min Act: -0.1700

Data Index: 248388 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.1791. Min Act: -0.1700

Data Index: 1461437 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.1949. Min Act: -0.1700

Data Index: 738281 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.1949. Min Act: -0.1700

Data Index: 517991 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.2106. Min Act: -0.1700

Data Index: 167944 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 3.4461. Min Range: -3.4461

Max Act: 3.1949. Min Act: -0.1700

Data Index: 872882 (C4 (Web Text))

Max Activating Token Index: 45