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

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

Neuron 1209 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.4687. Min Act: -0.1699

Data Index: 1045805 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.4687. Min Act: -0.1700

Data Index: 970385 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.4687. Min Act: -0.1700

Data Index: 1103392 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.4687. Min Act: -0.1700

Data Index: 313040 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.4373. Min Act: -0.1698

Data Index: 458993 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.4373. Min Act: -0.1700

Data Index: 176279 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.4373. Min Act: -0.1700

Data Index: 1309625 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.3746. Min Act: -0.1700

Data Index: 570418 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.3746. Min Act: -0.1700

Data Index: 452304 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.4373. Min Act: -0.1700

Data Index: 668272 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.4060. Min Act: -0.1700

Data Index: 968143 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.3746. Min Act: -0.1700

Data Index: 1126020 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.3432. Min Act: -0.1700

Data Index: 212281 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.3746. Min Act: -0.1700

Data Index: 797198 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.4060. Min Act: -0.1700

Data Index: 568219 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.3432. Min Act: -0.1700

Data Index: 1124328 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.3746. Min Act: -0.1700

Data Index: 143450 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.3746. Min Act: -0.1699

Data Index: 1280014 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.3432. Min Act: -0.1700

Data Index: 404040 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 3.4687. Min Range: -3.4687

Max Act: 3.2804. Min Act: -0.1700

Data Index: 141259 (C4 (Web Text))

Max Activating Token Index: 632