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

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

Neuron 591 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.6030. Min Act: -0.1700

Data Index: 323479 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.3530. Min Act: -0.1700

Data Index: 638515 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.3530. Min Act: -0.1696

Data Index: 48853 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.2905. Min Act: -0.1700

Data Index: 925657 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.2280. Min Act: -0.1700

Data Index: 424154 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.1967. Min Act: -0.1700

Data Index: 586252 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.2280. Min Act: -0.1699

Data Index: 780420 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.1967. Min Act: -0.1700

Data Index: 1330825 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.1655. Min Act: -0.1699

Data Index: 142286 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.2280. Min Act: -0.1700

Data Index: 1220711 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.1967. Min Act: -0.1699

Data Index: 499358 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.1342. Min Act: -0.1700

Data Index: 496287 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.1655. Min Act: -0.1697

Data Index: 519909 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.1342. Min Act: -0.1700

Data Index: 556389 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.0717. Min Act: -0.1700

Data Index: 1332062 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.1655. Min Act: -0.1700

Data Index: 759115 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.1030. Min Act: -0.1700

Data Index: 1089516 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.0717. Min Act: -0.1700

Data Index: 204360 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.1030. Min Act: -0.1700

Data Index: 1212150 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 5.6030. Min Range: -5.6030

Max Act: 5.0717. Min Act: -0.1700

Data Index: 573938 (C4 (Web Text))

Max Activating Token Index: 716