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

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

Neuron 1476 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8985. Min Act: -0.1700

Data Index: 482614 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8985. Min Act: -0.1700

Data Index: 1144281 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8985. Min Act: -0.1700

Data Index: 672475 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8985. Min Act: -0.1700

Data Index: 1040695 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8359. Min Act: -0.1700

Data Index: 771108 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8359. Min Act: -0.1700

Data Index: 470832 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8359. Min Act: -0.1700

Data Index: 247999 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8046. Min Act: -0.1700

Data Index: 1417982 (Python Code)

Max Activating Token Index: 437

Text #8

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8046. Min Act: -0.1700

Data Index: 1630390 (Python Code)

Max Activating Token Index: 315

Text #9

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7734. Min Act: -0.1700

Data Index: 656113 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7734. Min Act: -0.1700

Data Index: 281486 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7577. Min Act: -0.1700

Data Index: 238951 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7421. Min Act: -0.1700

Data Index: 811388 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7734. Min Act: -0.1700

Data Index: 996788 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7734. Min Act: -0.1700

Data Index: 515893 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7577. Min Act: -0.1700

Data Index: 936041 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7734. Min Act: -0.1700

Data Index: 12521 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7577. Min Act: -0.1700

Data Index: 636059 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7734. Min Act: -0.1700

Data Index: 625583 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7734. Min Act: -0.1700

Data Index: 1131003 (C4 (Web Text))

Max Activating Token Index: 1009