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

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

Neuron 245 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.9777. Min Act: -0.1700

Data Index: 1284170 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.8213. Min Act: -0.1700

Data Index: 266276 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7587. Min Act: -0.1700

Data Index: 32063 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7587. Min Act: -0.1700

Data Index: 483967 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7274. Min Act: -0.1700

Data Index: 717821 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7587. Min Act: -0.1700

Data Index: 319414 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.6961. Min Act: -0.1700

Data Index: 986649 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.6961. Min Act: -0.1700

Data Index: 977522 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7274. Min Act: -0.1700

Data Index: 1332585 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.6648. Min Act: -0.1700

Data Index: 649582 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.6335. Min Act: -0.1700

Data Index: 538955 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.6022. Min Act: -0.1700

Data Index: 965058 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.6335. Min Act: -0.1700

Data Index: 507308 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.6022. Min Act: -0.1700

Data Index: 1066272 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.6022. Min Act: -0.1700

Data Index: 452371 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.5709. Min Act: -0.1700

Data Index: 357903 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.5709. Min Act: -0.1700

Data Index: 1105391 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.6335. Min Act: -0.1700

Data Index: 392724 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.5709. Min Act: -0.1700

Data Index: 626367 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.5709. Min Act: -0.1700

Data Index: 805616 (C4 (Web Text))

Max Activating Token Index: 14