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

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

Neuron 1151 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: 4.2510. Min Range: -4.2510

Max Act: 4.2510. Min Act: -0.1479

Data Index: 256439 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.0202. Min Act: -0.1389

Data Index: 280791 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.9486. Min Act: -0.1700

Data Index: 445999 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.9503. Min Act: -0.1683

Data Index: 1221935 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.9243. Min Act: -0.1691

Data Index: 838463 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.9478. Min Act: -0.1700

Data Index: 964646 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.9414. Min Act: -0.1684

Data Index: 843663 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.9135. Min Act: -0.1467

Data Index: 1352927 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.9403. Min Act: -0.1677

Data Index: 605953 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.9092. Min Act: -0.1700

Data Index: 441206 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.9078. Min Act: -0.1699

Data Index: 1260112 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.8613. Min Act: -0.1699

Data Index: 484624 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.8828. Min Act: -0.1698

Data Index: 926311 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.8736. Min Act: -0.1680

Data Index: 883196 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.8682. Min Act: -0.1699

Data Index: 355575 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.8214. Min Act: -0.1700

Data Index: 154693 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.7893. Min Act: -0.1700

Data Index: 585209 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.7946. Min Act: -0.1700

Data Index: 332392 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.7890. Min Act: -0.1700

Data Index: 614232 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.7634. Min Act: -0.1700

Data Index: 148336 (C4 (Web Text))

Max Activating Token Index: 617