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

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

Neuron 1612 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: 8.4774. Min Range: -8.4774

Max Act: 8.4774. Min Act: -0.1700

Data Index: 605013 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.3856. Min Act: -0.1700

Data Index: 220079 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.3598. Min Act: -0.1700

Data Index: 1342491 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.2502. Min Act: -0.1700

Data Index: 1340153 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.1236. Min Act: -0.1700

Data Index: 82237 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.1810. Min Act: -0.1700

Data Index: 1161872 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.1559. Min Act: -0.1700

Data Index: 368530 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.1671. Min Act: -0.1700

Data Index: 988259 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.0855. Min Act: -0.1700

Data Index: 938941 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.0282. Min Act: -0.1700

Data Index: 641641 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.0074. Min Act: -0.1700

Data Index: 687403 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 8.4774. Min Range: -8.4774

Max Act: 7.9647. Min Act: -0.1700

Data Index: 497132 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 8.4774. Min Range: -8.4774

Max Act: 7.9717. Min Act: -0.1700

Data Index: 505257 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.0058. Min Act: -0.1700

Data Index: 523960 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 8.4774. Min Range: -8.4774

Max Act: 8.0207. Min Act: -0.1700

Data Index: 202083 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 8.4774. Min Range: -8.4774

Max Act: 7.9625. Min Act: -0.1700

Data Index: 659338 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 8.4774. Min Range: -8.4774

Max Act: 7.9409. Min Act: -0.1700

Data Index: 792670 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 8.4774. Min Range: -8.4774

Max Act: 7.8704. Min Act: -0.1700

Data Index: 59570 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 8.4774. Min Range: -8.4774

Max Act: 7.8952. Min Act: -0.1700

Data Index: 547910 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 8.4774. Min Range: -8.4774

Max Act: 7.9084. Min Act: -0.1700

Data Index: 351924 (C4 (Web Text))

Max Activating Token Index: 44