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

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

Neuron 2007 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: 5.1904. Min Range: -5.1904

Max Act: 5.0967. Min Act: -0.1700

Data Index: 816699 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 5.1904. Min Range: -5.1904

Max Act: 5.1904. Min Act: -0.1700

Data Index: 33911 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 5.1904. Min Range: -5.1904

Max Act: 5.0654. Min Act: -0.1700

Data Index: 589290 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 5.1904. Min Range: -5.1904

Max Act: 5.0029. Min Act: -0.1700

Data Index: 740558 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.8779. Min Act: -0.1700

Data Index: 509352 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.8467. Min Act: -0.1700

Data Index: 991752 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.8467. Min Act: -0.1700

Data Index: 327295 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.8779. Min Act: -0.1700

Data Index: 160991 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.8779. Min Act: -0.1700

Data Index: 444565 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.8467. Min Act: -0.1700

Data Index: 506800 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.8154. Min Act: -0.1700

Data Index: 230797 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.8467. Min Act: -0.1700

Data Index: 1118597 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.8467. Min Act: -0.1700

Data Index: 741812 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.8154. Min Act: -0.1700

Data Index: 309372 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.7529. Min Act: -0.1700

Data Index: 451131 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.6904. Min Act: -0.1700

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.6592. Min Act: -0.1700

Data Index: 68646 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.6279. Min Act: -0.1700

Data Index: 1065328 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.6592. Min Act: -0.1700

Data Index: 19249 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 5.1904. Min Range: -5.1904

Max Act: 4.6592. Min Act: -0.1700

Data Index: 206299 (C4 (Web Text))

Max Activating Token Index: 392