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

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

Neuron 1816 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0785. Min Range: -3.0785

Max Act: 3.0785. Min Act: -0.1700

Data Index: 664301 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 3.0785. Min Range: -3.0785

Max Act: 3.0785. Min Act: -0.1700

Data Index: 498627 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.9362. Min Act: -0.1700

Data Index: 671974 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.9362. Min Act: -0.1700

Data Index: 32104 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.9204. Min Act: -0.1700

Data Index: 946471 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.9045. Min Act: -0.1700

Data Index: 261712 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.9204. Min Act: -0.1700

Data Index: 115113 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.9045. Min Act: -0.1700

Data Index: 111235 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.8728. Min Act: -0.1700

Data Index: 711913 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.8887. Min Act: -0.1700

Data Index: 792409 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.8887. Min Act: -0.1700

Data Index: 295044 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.9045. Min Act: -0.1700

Data Index: 981515 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.9045. Min Act: -0.1700

Data Index: 1272368 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.8569. Min Act: -0.1700

Data Index: 242920 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.8728. Min Act: -0.1700

Data Index: 992776 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.8410. Min Act: -0.1700

Data Index: 751594 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.8410. Min Act: -0.1700

Data Index: 981078 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.8410. Min Act: -0.1700

Data Index: 139994 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.8410. Min Act: -0.1700

Data Index: 112774 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.8251. Min Act: -0.1700

Data Index: 544325 (C4 (Web Text))

Max Activating Token Index: 14