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

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

Neuron 1757 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: 7.0391. Min Range: -7.0391

Max Act: 7.0391. Min Act: -0.1700

Data Index: 568842 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.7891. Min Act: -0.1700

Data Index: 934147 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.7891. Min Act: -0.1699

Data Index: 927852 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.7110. Min Act: -0.1700

Data Index: 1357705 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.6485. Min Act: -0.1700

Data Index: 201410 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.6953. Min Act: -0.1700

Data Index: 770812 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.6172. Min Act: -0.1700

Data Index: 222237 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.6016. Min Act: -0.1700

Data Index: 931482 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5547. Min Act: -0.1700

Data Index: 254331 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5703. Min Act: -0.1700

Data Index: 680301 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4297. Min Act: -0.1700

Data Index: 1284381 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5391. Min Act: -0.1700

Data Index: 970517 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5391. Min Act: -0.1700

Data Index: 874506 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.3985. Min Act: -0.1700

Data Index: 292042 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.5703. Min Act: -0.1700

Data Index: 712269 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4453. Min Act: -0.1700

Data Index: 896359 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4453. Min Act: -0.1700

Data Index: 690001 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.3828. Min Act: -0.1700

Data Index: 1072800 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.2891. Min Act: -0.1700

Data Index: 165431 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 7.0391. Min Range: -7.0391

Max Act: 6.4610. Min Act: -0.1700

Data Index: 1337014 (C4 (Web Text))

Max Activating Token Index: 747