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

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

Neuron 1854 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: 2.9962. Min Range: -2.9962

Max Act: 2.9927. Min Act: -0.1700

Data Index: 519474 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.9890. Min Act: -0.1700

Data Index: 1597742 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.9962. Min Act: -0.1700

Data Index: 915560 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.9957. Min Act: -0.1700

Data Index: 928002 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.9569. Min Act: -0.1700

Data Index: 126476 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.9587. Min Act: -0.1700

Data Index: 916252 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.9456. Min Act: -0.1700

Data Index: 590442 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.9288. Min Act: -0.1700

Data Index: 420295 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.8963. Min Act: -0.1700

Data Index: 1423238 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.9215. Min Act: -0.1700

Data Index: 1403582 (Python Code)

Max Activating Token Index: 785

Text #10

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.9127. Min Act: -0.1700

Data Index: 666848 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.8984. Min Act: -0.1700

Data Index: 1070346 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.9198. Min Act: -0.1700

Data Index: 1138257 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.9018. Min Act: -0.1700

Data Index: 1236749 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.8906. Min Act: -0.1700

Data Index: 752341 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.8469. Min Act: -0.1700

Data Index: 1036618 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.8803. Min Act: -0.1700

Data Index: 1392707 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.8594. Min Act: -0.1700

Data Index: 1639868 (Python Code)

Max Activating Token Index: 641

Text #18

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.8609. Min Act: -0.1700

Data Index: 1632050 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 2.9962. Min Range: -2.9962

Max Act: 2.8746. Min Act: -0.1700

Data Index: 1649841 (Python Code)

Max Activating Token Index: 1023