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

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

Neuron 1987 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.2551. Min Act: -0.1700

Data Index: 584376 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.2551. Min Act: -0.1700

Data Index: 281041 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.1765. Min Act: -0.1700

Data Index: 233952 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.1292. Min Act: -0.1700

Data Index: 1341264 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.1450. Min Act: -0.1700

Data Index: 498109 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.1292. Min Act: -0.1700

Data Index: 1031287 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.1450. Min Act: -0.1700

Data Index: 177537 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.0977. Min Act: -0.1700

Data Index: 568485 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.1135. Min Act: -0.1700

Data Index: 834361 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.0819. Min Act: -0.1700

Data Index: 1353795 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.1135. Min Act: -0.1700

Data Index: 796086 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.0819. Min Act: -0.1700

Data Index: 358453 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.0977. Min Act: -0.1700

Data Index: 1261997 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.0819. Min Act: -0.1700

Data Index: 530943 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.0819. Min Act: -0.1700

Data Index: 1060594 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.0977. Min Act: -0.1700

Data Index: 812436 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.0977. Min Act: -0.1700

Data Index: 1353263 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.0662. Min Act: -0.1700

Data Index: 1230116 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.0346. Min Act: -0.1700

Data Index: 1349088 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 3.2551. Min Range: -3.2551

Max Act: 3.0346. Min Act: -0.1700

Data Index: 54420 (C4 (Web Text))

Max Activating Token Index: 771