Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1490 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.4111. Min Act: -0.1700

Data Index: 1288915 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.3326. Min Act: -0.1700

Data Index: 1312384 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.3012. Min Act: -0.1700

Data Index: 770536 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.2855. Min Act: -0.1700

Data Index: 965628 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.2698. Min Act: -0.1700

Data Index: 810663 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.2698. Min Act: -0.1700

Data Index: 243167 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.2384. Min Act: -0.1700

Data Index: 866486 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.2384. Min Act: -0.1700

Data Index: 824182 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.2384. Min Act: -0.1700

Data Index: 839474 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.2069. Min Act: -0.1700

Data Index: 468923 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.1912. Min Act: -0.1700

Data Index: 660307 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.2069. Min Act: -0.1700

Data Index: 850393 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.1755. Min Act: -0.1700

Data Index: 1320563 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.1597. Min Act: -0.1700

Data Index: 789146 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.1597. Min Act: -0.1700

Data Index: 1013973 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.1597. Min Act: -0.1700

Data Index: 34239 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.1440. Min Act: -0.1700

Data Index: 512557 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.0967. Min Act: -0.1700

Data Index: 462925 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.1125. Min Act: -0.1700

Data Index: 658363 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 3.4111. Min Range: -3.4111

Max Act: 3.0967. Min Act: -0.1700

Data Index: 467251 (C4 (Web Text))

Max Activating Token Index: 329