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

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

Neuron 1191 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.8096. Min Act: -0.1700

Data Index: 326974 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7940. Min Act: -0.1700

Data Index: 1280635 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.8253. Min Act: -0.1700

Data Index: 1459789 (Python Code)

Max Activating Token Index: 321

Text #3

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.8096. Min Act: -0.1700

Data Index: 1062088 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.8096. Min Act: -0.1700

Data Index: 973052 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7783. Min Act: -0.1700

Data Index: 648442 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7627. Min Act: -0.1700

Data Index: 382114 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7783. Min Act: -0.1700

Data Index: 593424 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7471. Min Act: -0.1700

Data Index: 773923 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7627. Min Act: -0.1700

Data Index: 421392 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7783. Min Act: -0.1700

Data Index: 3188 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7783. Min Act: -0.1700

Data Index: 710151 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7783. Min Act: -0.1700

Data Index: 711738 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7627. Min Act: -0.1700

Data Index: 484744 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7627. Min Act: -0.1700

Data Index: 1226267 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7158. Min Act: -0.1700

Data Index: 705400 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7314. Min Act: -0.1700

Data Index: 943575 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7471. Min Act: -0.1700

Data Index: 421784 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7471. Min Act: -0.1700

Data Index: 255016 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 3.8253. Min Range: -3.8253

Max Act: 3.7627. Min Act: -0.1700

Data Index: 173703 (C4 (Web Text))

Max Activating Token Index: 416