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

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

Neuron 1224 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: 3.4656. Min Range: -3.4656

Max Act: 3.4656. Min Act: -0.1700

Data Index: 384450 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.3087. Min Act: -0.1700

Data Index: 1247441 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.2301. Min Act: -0.1700

Data Index: 924045 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.1986. Min Act: -0.1700

Data Index: 55130 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.2144. Min Act: -0.1700

Data Index: 793493 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.1829. Min Act: -0.1700

Data Index: 445323 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.1672. Min Act: -0.1700

Data Index: 341905 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.1199. Min Act: -0.1700

Data Index: 459521 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.1357. Min Act: -0.1700

Data Index: 856741 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.1514. Min Act: -0.1700

Data Index: 261538 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.1199. Min Act: -0.1700

Data Index: 747271 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.1042. Min Act: -0.1700

Data Index: 289505 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.0726. Min Act: -0.1700

Data Index: 1114621 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.0410. Min Act: -0.1700

Data Index: 194681 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.0568. Min Act: -0.1700

Data Index: 297358 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.0568. Min Act: -0.1700

Data Index: 497161 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.0410. Min Act: -0.1700

Data Index: 434789 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.0568. Min Act: -0.1700

Data Index: 785560 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.0568. Min Act: -0.1700

Data Index: 632300 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 3.4656. Min Range: -3.4656

Max Act: 3.0252. Min Act: -0.1700

Data Index: 1004145 (C4 (Web Text))

Max Activating Token Index: 510