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

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

Neuron 914 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: 3.5852. Min Range: -3.5852

Max Act: 3.5852. Min Act: -0.1700

Data Index: 65681 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.4250. Min Act: -0.1700

Data Index: 518828 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.4119. Min Act: -0.1700

Data Index: 1435585 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3880. Min Act: -0.1700

Data Index: 790922 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3658. Min Act: -0.1700

Data Index: 946964 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3442. Min Act: -0.1700

Data Index: 802128 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3574. Min Act: -0.1700

Data Index: 791662 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3344. Min Act: -0.1700

Data Index: 1347222 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3847. Min Act: -0.1700

Data Index: 1330993 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3557. Min Act: -0.1700

Data Index: 308125 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3259. Min Act: -0.1700

Data Index: 39874 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.2633. Min Act: -0.1700

Data Index: 1279344 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.2612. Min Act: -0.1700

Data Index: 834942 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.2617. Min Act: -0.1700

Data Index: 760553 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.2555. Min Act: -0.1700

Data Index: 335567 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.2639. Min Act: -0.1700

Data Index: 1352697 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.2793. Min Act: -0.1700

Data Index: 807702 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.2774. Min Act: -0.1700

Data Index: 1603960 (Python Code)

Max Activating Token Index: 20

Text #18

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.2515. Min Act: -0.1700

Data Index: 1501292 (Python Code)

Max Activating Token Index: 481

Text #19

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.2493. Min Act: -0.1700

Data Index: 83052 (C4 (Web Text))

Max Activating Token Index: 1023