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

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

Neuron 1892 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: 3.8070. Min Range: -3.8070

Max Act: 3.8070. Min Act: -0.1700

Data Index: 1602940 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.6355. Min Act: -0.1700

Data Index: 1387815 (Python Code)

Max Activating Token Index: 791

Text #2

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.6008. Min Act: -0.1700

Data Index: 164200 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.6150. Min Act: -0.1700

Data Index: 1422764 (Python Code)

Max Activating Token Index: 676

Text #4

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.5781. Min Act: -0.1699

Data Index: 1524253 (Python Code)

Max Activating Token Index: 332

Text #5

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.5650. Min Act: -0.1700

Data Index: 841809 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.5542. Min Act: -0.1700

Data Index: 1425007 (Python Code)

Max Activating Token Index: 132

Text #7

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.5404. Min Act: -0.1700

Data Index: 1647682 (Python Code)

Max Activating Token Index: 651

Text #8

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.5449. Min Act: -0.1700

Data Index: 1588065 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.5443. Min Act: -0.1700

Data Index: 243528 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.5379. Min Act: -0.1700

Data Index: 1642830 (Python Code)

Max Activating Token Index: 163

Text #11

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.5127. Min Act: -0.1700

Data Index: 1101708 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.4789. Min Act: -0.1700

Data Index: 999439 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.4843. Min Act: -0.1700

Data Index: 1199194 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.4689. Min Act: -0.1700

Data Index: 1356493 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.4697. Min Act: -0.1700

Data Index: 78780 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.4872. Min Act: -0.1700

Data Index: 1471384 (Python Code)

Max Activating Token Index: 811

Text #17

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.4648. Min Act: -0.1700

Data Index: 1492475 (Python Code)

Max Activating Token Index: 312

Text #18

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.4492. Min Act: -0.1700

Data Index: 1511723 (Python Code)

Max Activating Token Index: 741

Text #19

Max Range: 3.8070. Min Range: -3.8070

Max Act: 3.4008. Min Act: -0.1700

Data Index: 370875 (C4 (Web Text))

Max Activating Token Index: 103