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

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

Neuron 1222 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2448. Min Range: -5.2448

Max Act: 5.2448. Min Act: -0.1700

Data Index: 213215 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 5.2448. Min Range: -5.2448

Max Act: 5.0573. Min Act: -0.1700

Data Index: 738302 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 5.2448. Min Range: -5.2448

Max Act: 5.0573. Min Act: -0.1700

Data Index: 1228399 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 5.2448. Min Range: -5.2448

Max Act: 5.0886. Min Act: -0.1700

Data Index: 504120 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 5.2448. Min Range: -5.2448

Max Act: 5.0261. Min Act: -0.1700

Data Index: 1252656 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.9948. Min Act: -0.1700

Data Index: 1083825 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.9011. Min Act: -0.1700

Data Index: 826570 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.8698. Min Act: -0.1700

Data Index: 834560 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.9011. Min Act: -0.1700

Data Index: 880584 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.8386. Min Act: -0.1700

Data Index: 561290 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.9011. Min Act: -0.1700

Data Index: 594515 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.8073. Min Act: -0.1700

Data Index: 353724 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.8698. Min Act: -0.1700

Data Index: 161164 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.8698. Min Act: -0.1700

Data Index: 54430 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.8073. Min Act: -0.1700

Data Index: 327518 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.8386. Min Act: -0.1700

Data Index: 672036 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.7761. Min Act: -0.1700

Data Index: 834657 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.7761. Min Act: -0.1700

Data Index: 877141 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.8073. Min Act: -0.1700

Data Index: 358998 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 5.2448. Min Range: -5.2448

Max Act: 4.8073. Min Act: -0.1700

Data Index: 797396 (C4 (Web Text))

Max Activating Token Index: 208