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

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

Neuron 726 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: 3.6705. Min Range: -3.6705

Max Act: 3.6705. Min Act: -0.1697

Data Index: 1090404 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.6300. Min Act: -0.1699

Data Index: 1279402 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.6032. Min Act: -0.1700

Data Index: 1352151 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.5631. Min Act: -0.1700

Data Index: 369541 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.5687. Min Act: -0.1698

Data Index: 431932 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.5239. Min Act: -0.1700

Data Index: 597310 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.5232. Min Act: -0.1700

Data Index: 602872 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4950. Min Act: -0.1700

Data Index: 935165 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4886. Min Act: -0.1700

Data Index: 368043 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4757. Min Act: -0.1700

Data Index: 224278 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4574. Min Act: -0.1700

Data Index: 10532 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4256. Min Act: -0.1700

Data Index: 1019869 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4311. Min Act: -0.1699

Data Index: 580630 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4129. Min Act: -0.1700

Data Index: 1164175 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4470. Min Act: -0.1700

Data Index: 1300809 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4349. Min Act: -0.1700

Data Index: 692064 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4536. Min Act: -0.1700

Data Index: 482570 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4466. Min Act: -0.1700

Data Index: 750732 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4300. Min Act: -0.1700

Data Index: 1037835 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.6705. Min Range: -3.6705

Max Act: 3.4259. Min Act: -0.1700

Data Index: 1071058 (C4 (Web Text))

Max Activating Token Index: 975