Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 909 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.5490. Min Act: -0.1700

Data Index: 1012764 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.5198. Min Act: -0.1700

Data Index: 687754 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.5013. Min Act: -0.1700

Data Index: 606107 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.4669. Min Act: -0.1699

Data Index: 1324795 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.4584. Min Act: -0.1700

Data Index: 336892 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.4389. Min Act: -0.1700

Data Index: 445704 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.4088. Min Act: -0.1700

Data Index: 441502 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.4183. Min Act: -0.1700

Data Index: 611957 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.4335. Min Act: -0.1700

Data Index: 926184 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.4384. Min Act: -0.1700

Data Index: 857335 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.4311. Min Act: -0.1700

Data Index: 665179 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.4174. Min Act: -0.1700

Data Index: 11389 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.3848. Min Act: -0.1700

Data Index: 295481 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.3871. Min Act: -0.1699

Data Index: 664591 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.3860. Min Act: -0.1700

Data Index: 544523 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.4077. Min Act: -0.1700

Data Index: 878312 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.3993. Min Act: -0.1700

Data Index: 247143 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.3993. Min Act: -0.1700

Data Index: 605413 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.4007. Min Act: -0.1699

Data Index: 274526 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 4.5490. Min Range: -4.5490

Max Act: 4.3889. Min Act: -0.1700

Data Index: 97720 (C4 (Web Text))

Max Activating Token Index: 648