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

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

Neuron 493 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.6997. Min Act: -0.1700

Data Index: 794290 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.5122. Min Act: -0.1700

Data Index: 734819 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.4810. Min Act: -0.1700

Data Index: 1030803 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.4810. Min Act: -0.1700

Data Index: 2535 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.3872. Min Act: -0.1700

Data Index: 548550 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.3247. Min Act: -0.1700

Data Index: 527721 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.2935. Min Act: -0.1700

Data Index: 232515 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.2935. Min Act: -0.1700

Data Index: 41908 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.3247. Min Act: -0.1700

Data Index: 240447 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.3247. Min Act: -0.1700

Data Index: 773230 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.2310. Min Act: -0.1700

Data Index: 1006681 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.2622. Min Act: -0.1700

Data Index: 855934 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.2622. Min Act: -0.1700

Data Index: 1281380 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.2310. Min Act: -0.1700

Data Index: 1186542 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.2622. Min Act: -0.1700

Data Index: 803722 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.2310. Min Act: -0.1700

Data Index: 1212958 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.2310. Min Act: -0.1700

Data Index: 1222220 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.2310. Min Act: -0.1700

Data Index: 948804 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.1685. Min Act: -0.1700

Data Index: 525370 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 5.6997. Min Range: -5.6997

Max Act: 5.1060. Min Act: -0.1700

Data Index: 537422 (C4 (Web Text))

Max Activating Token Index: 424