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

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

Neuron 967 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: 3.9780. Min Range: -3.9780

Max Act: 3.9611. Min Act: -0.1700

Data Index: 371607 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.9780. Min Act: -0.1700

Data Index: 59645 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.9220. Min Act: -0.1700

Data Index: 45859 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.9348. Min Act: -0.1700

Data Index: 197601 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.9095. Min Act: -0.1700

Data Index: 442077 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.8354. Min Act: -0.1700

Data Index: 535054 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.8259. Min Act: -0.1700

Data Index: 969614 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.7929. Min Act: -0.1700

Data Index: 190935 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.8071. Min Act: -0.1700

Data Index: 853146 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.8092. Min Act: -0.1700

Data Index: 969700 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.7985. Min Act: -0.1700

Data Index: 319982 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.7768. Min Act: -0.1700

Data Index: 1255396 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.8076. Min Act: -0.1700

Data Index: 1182159 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.7641. Min Act: -0.1700

Data Index: 472393 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.7452. Min Act: -0.1700

Data Index: 1351874 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.7336. Min Act: -0.1700

Data Index: 571253 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.7548. Min Act: -0.1700

Data Index: 194416 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.7191. Min Act: -0.1700

Data Index: 1290536 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.6961. Min Act: -0.1700

Data Index: 243999 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 3.9780. Min Range: -3.9780

Max Act: 3.7179. Min Act: -0.1700

Data Index: 146103 (C4 (Web Text))

Max Activating Token Index: 15