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

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

Neuron 1815 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: 3.9979. Min Range: -3.9979

Max Act: 3.9979. Min Act: -0.1700

Data Index: 135572 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.9623. Min Act: -0.1700

Data Index: 546769 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.9178. Min Act: -0.1700

Data Index: 428248 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.8722. Min Act: -0.1700

Data Index: 99039 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.8338. Min Act: -0.1700

Data Index: 589035 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.8473. Min Act: -0.1700

Data Index: 265235 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7955. Min Act: -0.1700

Data Index: 276422 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.8081. Min Act: -0.1700

Data Index: 1340197 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7701. Min Act: -0.1700

Data Index: 805816 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.8070. Min Act: -0.1700

Data Index: 847068 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7572. Min Act: -0.1700

Data Index: 1297560 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7688. Min Act: -0.1700

Data Index: 753776 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7566. Min Act: -0.1700

Data Index: 469487 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7409. Min Act: -0.1700

Data Index: 55748 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7264. Min Act: -0.1700

Data Index: 1213777 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7389. Min Act: -0.1700

Data Index: 193967 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7817. Min Act: -0.1700

Data Index: 517372 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7492. Min Act: -0.1700

Data Index: 1295457 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7562. Min Act: -0.1700

Data Index: 363713 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 3.9979. Min Range: -3.9979

Max Act: 3.7371. Min Act: -0.1700

Data Index: 983132 (C4 (Web Text))

Max Activating Token Index: 690