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

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

Neuron 1845 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: 4.2786. Min Range: -4.2786

Max Act: 4.2786. Min Act: -0.1700

Data Index: 584697 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 4.2786. Min Range: -4.2786

Max Act: 4.1559. Min Act: -0.1700

Data Index: 777101 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 4.2786. Min Range: -4.2786

Max Act: 4.1158. Min Act: -0.1700

Data Index: 1109607 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 4.2786. Min Range: -4.2786

Max Act: 4.0895. Min Act: -0.1700

Data Index: 541980 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 4.2786. Min Range: -4.2786

Max Act: 4.0422. Min Act: -0.1700

Data Index: 1271911 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.9783. Min Act: -0.1700

Data Index: 1586117 (Python Code)

Max Activating Token Index: 158

Text #6

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.9595. Min Act: -0.1700

Data Index: 737965 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.9731. Min Act: -0.1700

Data Index: 1434535 (Python Code)

Max Activating Token Index: 418

Text #8

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.9740. Min Act: -0.1700

Data Index: 735770 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.9140. Min Act: -0.1700

Data Index: 1645446 (Python Code)

Max Activating Token Index: 257

Text #10

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.8729. Min Act: -0.1700

Data Index: 1163500 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.8690. Min Act: -0.1699

Data Index: 1455224 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.8683. Min Act: -0.1700

Data Index: 1411063 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.8442. Min Act: -0.1700

Data Index: 114825 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.8682. Min Act: -0.1700

Data Index: 1201765 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.8770. Min Act: -0.1699

Data Index: 381100 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.8565. Min Act: -0.1700

Data Index: 1235141 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.8511. Min Act: -0.1700

Data Index: 1048485 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.8670. Min Act: -0.1700

Data Index: 918705 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 4.2786. Min Range: -4.2786

Max Act: 3.8214. Min Act: -0.1699

Data Index: 902062 (C4 (Web Text))

Max Activating Token Index: 250