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

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

Neuron 4 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: 5.7129. Min Range: -5.7129

Max Act: 5.7129. Min Act: -0.1700

Data Index: 133492 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.7129. Min Act: -0.1700

Data Index: 356475 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.6192. Min Act: -0.1700

Data Index: 754154 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.5567. Min Act: -0.1700

Data Index: 152253 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.5567. Min Act: -0.1700

Data Index: 96556 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.5254. Min Act: -0.1700

Data Index: 1040737 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.4942. Min Act: -0.1700

Data Index: 506873 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.5254. Min Act: -0.1700

Data Index: 1305725 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.4942. Min Act: -0.1700

Data Index: 306362 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.4629. Min Act: -0.1700

Data Index: 359937 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.4629. Min Act: -0.1700

Data Index: 115794 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.4317. Min Act: -0.1700

Data Index: 426188 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.4004. Min Act: -0.1699

Data Index: 690545 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.4629. Min Act: -0.1700

Data Index: 1318194 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.4629. Min Act: -0.1700

Data Index: 457274 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.4942. Min Act: -0.1700

Data Index: 843435 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.4317. Min Act: -0.1700

Data Index: 343433 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.3692. Min Act: -0.1700

Data Index: 1053376 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.3692. Min Act: -0.1700

Data Index: 302774 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 5.7129. Min Range: -5.7129

Max Act: 5.3692. Min Act: -0.1700

Data Index: 178706 (C4 (Web Text))

Max Activating Token Index: 599