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

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

Neuron 926 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: 3.3919. Min Range: -3.3919

Max Act: 3.3919. Min Act: -0.1700

Data Index: 736209 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.3444. Min Act: -0.1700

Data Index: 967127 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.3220. Min Act: -0.1700

Data Index: 69701 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.3378. Min Act: -0.1700

Data Index: 445232 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.3300. Min Act: -0.1700

Data Index: 469815 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2885. Min Act: -0.1700

Data Index: 333261 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2961. Min Act: -0.1700

Data Index: 685186 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.3000. Min Act: -0.1700

Data Index: 807911 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.3040. Min Act: -0.1700

Data Index: 452180 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2729. Min Act: -0.1700

Data Index: 305570 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2893. Min Act: -0.1700

Data Index: 266197 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2925. Min Act: -0.1698

Data Index: 1348173 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2821. Min Act: -0.1700

Data Index: 411644 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2895. Min Act: -0.1700

Data Index: 984862 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2532. Min Act: -0.1700

Data Index: 148003 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2683. Min Act: -0.1700

Data Index: 966787 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2556. Min Act: -0.1700

Data Index: 124250 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2659. Min Act: -0.1700

Data Index: 1033408 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2616. Min Act: -0.1700

Data Index: 545289 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 3.3919. Min Range: -3.3919

Max Act: 3.2343. Min Act: -0.1700

Data Index: 432507 (C4 (Web Text))

Max Activating Token Index: 610