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

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

Neuron 1439 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: 5.7784. Min Range: -5.7784

Max Act: 5.7784. Min Act: -0.1700

Data Index: 543885 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.6846. Min Act: -0.1700

Data Index: 1331078 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.6846. Min Act: -0.1700

Data Index: 74588 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.6534. Min Act: -0.1700

Data Index: 574855 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.7159. Min Act: -0.1700

Data Index: 395782 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.6221. Min Act: -0.1700

Data Index: 482765 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.6846. Min Act: -0.1700

Data Index: 1302060 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.6221. Min Act: -0.1700

Data Index: 857557 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.6221. Min Act: -0.1700

Data Index: 601889 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.6534. Min Act: -0.1700

Data Index: 1154531 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.5909. Min Act: -0.1700

Data Index: 699188 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.6534. Min Act: -0.1700

Data Index: 168669 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.6221. Min Act: -0.1700

Data Index: 959585 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.6534. Min Act: -0.1700

Data Index: 245256 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.5909. Min Act: -0.1700

Data Index: 100002 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.5596. Min Act: -0.1700

Data Index: 470711 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.5596. Min Act: -0.1700

Data Index: 103938 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.5284. Min Act: -0.1700

Data Index: 978534 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.5909. Min Act: -0.1700

Data Index: 677523 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 5.7784. Min Range: -5.7784

Max Act: 5.5909. Min Act: -0.1700

Data Index: 74562 (C4 (Web Text))

Max Activating Token Index: 129