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

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

Neuron 523 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: 3.7292. Min Range: -3.7292

Max Act: 3.7292. Min Act: -0.1700

Data Index: 501874 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4787. Min Act: -0.1700

Data Index: 1319459 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.5100. Min Act: -0.1700

Data Index: 202735 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4474. Min Act: -0.1700

Data Index: 926559 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4003. Min Act: -0.1700

Data Index: 510516 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4003. Min Act: -0.1700

Data Index: 661278 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4003. Min Act: -0.1700

Data Index: 599422 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3846. Min Act: -0.1700

Data Index: 1234137 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3689. Min Act: -0.1700

Data Index: 311762 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3689. Min Act: -0.1700

Data Index: 182090 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4160. Min Act: -0.1700

Data Index: 20953 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3846. Min Act: -0.1700

Data Index: 1082522 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4160. Min Act: -0.1700

Data Index: 757659 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3532. Min Act: -0.1700

Data Index: 236270 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3532. Min Act: -0.1700

Data Index: 288950 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3532. Min Act: -0.1700

Data Index: 595314 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3532. Min Act: -0.1700

Data Index: 24454 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3218. Min Act: -0.1700

Data Index: 1072064 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3532. Min Act: -0.1700

Data Index: 393038 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3689. Min Act: -0.1700

Data Index: 1086772 (C4 (Web Text))

Max Activating Token Index: 868