Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 990 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0801. Min Range: -3.0801

Max Act: 3.0801. Min Act: -0.1700

Data Index: 843828 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 3.0801. Min Range: -3.0801

Max Act: 3.0501. Min Act: -0.1700

Data Index: 939514 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 3.0801. Min Range: -3.0801

Max Act: 3.0349. Min Act: -0.1700

Data Index: 872472 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9969. Min Act: -0.1700

Data Index: 98121 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9842. Min Act: -0.1700

Data Index: 342638 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9625. Min Act: -0.1700

Data Index: 1109412 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9643. Min Act: -0.1700

Data Index: 1298910 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9188. Min Act: -0.1700

Data Index: 1457079 (Python Code)

Max Activating Token Index: 331

Text #8

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9166. Min Act: -0.1700

Data Index: 167493 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9273. Min Act: -0.1700

Data Index: 856526 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9250. Min Act: -0.1700

Data Index: 327526 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9146. Min Act: -0.1700

Data Index: 316091 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.8960. Min Act: -0.1700

Data Index: 1024843 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9085. Min Act: -0.1700

Data Index: 1004084 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9059. Min Act: -0.1700

Data Index: 119397 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.8815. Min Act: -0.1700

Data Index: 643520 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.8888. Min Act: -0.1700

Data Index: 59448 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.8791. Min Act: -0.1700

Data Index: 1236753 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.8842. Min Act: -0.1700

Data Index: 253478 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.8827. Min Act: -0.1700

Data Index: 794650 (C4 (Web Text))

Max Activating Token Index: 457