Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 631 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.6412. Min Act: -0.1700

Data Index: 258842 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.6098. Min Act: -0.1700

Data Index: 496045 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.6412. Min Act: -0.1700

Data Index: 487517 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5472. Min Act: -0.1700

Data Index: 514003 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5472. Min Act: -0.1700

Data Index: 1306910 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5315. Min Act: -0.1700

Data Index: 1296829 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5315. Min Act: -0.1700

Data Index: 94671 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5159. Min Act: -0.1700

Data Index: 1528160 (Python Code)

Max Activating Token Index: 184

Text #8

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5159. Min Act: -0.1700

Data Index: 1415886 (Python Code)

Max Activating Token Index: 147

Text #9

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5159. Min Act: -0.1700

Data Index: 64988 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5159. Min Act: -0.1700

Data Index: 1357567 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5002. Min Act: -0.1700

Data Index: 121329 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5315. Min Act: -0.1700

Data Index: 62387 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5315. Min Act: -0.1700

Data Index: 572100 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5159. Min Act: -0.1700

Data Index: 1232301 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5002. Min Act: -0.1700

Data Index: 273349 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5002. Min Act: -0.1700

Data Index: 860181 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.5002. Min Act: -0.1700

Data Index: 215196 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.4845. Min Act: -0.1700

Data Index: 360671 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 3.6412. Min Range: -3.6412

Max Act: 3.4689. Min Act: -0.1700

Data Index: 439708 (C4 (Web Text))

Max Activating Token Index: 149