Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1889 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.3502. Min Range: -4.3502

Max Act: 4.3502. Min Act: -0.1700

Data Index: 104537 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 4.3502. Min Range: -4.3502

Max Act: 4.0509. Min Act: -0.1700

Data Index: 529024 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 4.3502. Min Range: -4.3502

Max Act: 4.0203. Min Act: -0.1700

Data Index: 673733 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 4.3502. Min Range: -4.3502

Max Act: 4.0358. Min Act: -0.1700

Data Index: 1149568 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 4.3502. Min Range: -4.3502

Max Act: 4.0086. Min Act: -0.1700

Data Index: 1342850 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 4.3502. Min Range: -4.3502

Max Act: 4.0153. Min Act: -0.1700

Data Index: 343804 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.9937. Min Act: -0.1700

Data Index: 218217 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.9836. Min Act: -0.1700

Data Index: 61380 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.9767. Min Act: -0.1700

Data Index: 968087 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.9545. Min Act: -0.1700

Data Index: 610322 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.9538. Min Act: -0.1700

Data Index: 1229133 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.9358. Min Act: -0.1700

Data Index: 526974 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.9315. Min Act: -0.1700

Data Index: 489830 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.9202. Min Act: -0.1700

Data Index: 675751 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.8824. Min Act: -0.1700

Data Index: 143834 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.8719. Min Act: -0.1700

Data Index: 1036143 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.8629. Min Act: -0.1700

Data Index: 498255 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.8600. Min Act: -0.1700

Data Index: 185031 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.8664. Min Act: -0.1699

Data Index: 564212 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 4.3502. Min Range: -4.3502

Max Act: 3.8678. Min Act: -0.1700

Data Index: 123402 (C4 (Web Text))

Max Activating Token Index: 796