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

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

Neuron 243 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: 4.1925. Min Range: -4.1925

Max Act: 4.1925. Min Act: -0.1700

Data Index: 1346306 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.1055. Min Act: -0.1700

Data Index: 572725 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0323. Min Act: -0.1700

Data Index: 248372 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0588. Min Act: -0.1700

Data Index: 766293 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0343. Min Act: -0.1700

Data Index: 338888 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0666. Min Act: -0.1700

Data Index: 1164326 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0364. Min Act: -0.1700

Data Index: 569444 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9847. Min Act: -0.1700

Data Index: 1050218 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9621. Min Act: -0.1700

Data Index: 950819 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9916. Min Act: -0.1700

Data Index: 1160610 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9736. Min Act: -0.1700

Data Index: 660678 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0016. Min Act: -0.1700

Data Index: 1140804 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9628. Min Act: -0.1700

Data Index: 433581 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9562. Min Act: -0.1700

Data Index: 661289 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9660. Min Act: -0.1700

Data Index: 1027742 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9681. Min Act: -0.1700

Data Index: 264088 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9609. Min Act: -0.1700

Data Index: 1021576 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9524. Min Act: -0.1700

Data Index: 993224 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9315. Min Act: -0.1700

Data Index: 987438 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9843. Min Act: -0.1700

Data Index: 417675 (C4 (Web Text))

Max Activating Token Index: 448