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

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

Neuron 1611 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: 5.0936. Min Range: -5.0936

Max Act: 5.0541. Min Act: -0.1700

Data Index: 1069075 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 5.0936. Min Range: -5.0936

Max Act: 5.0936. Min Act: -0.1700

Data Index: 971515 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 5.0936. Min Range: -5.0936

Max Act: 5.0911. Min Act: -0.1700

Data Index: 112397 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 5.0936. Min Range: -5.0936

Max Act: 5.0494. Min Act: -0.1700

Data Index: 1067633 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9991. Min Act: -0.1700

Data Index: 632830 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9856. Min Act: -0.1700

Data Index: 977657 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 5.0936. Min Range: -5.0936

Max Act: 5.0105. Min Act: -0.1700

Data Index: 583926 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9691. Min Act: -0.1700

Data Index: 952964 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9507. Min Act: -0.1700

Data Index: 218112 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9467. Min Act: -0.1700

Data Index: 543465 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9619. Min Act: -0.1700

Data Index: 1230075 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9694. Min Act: -0.1700

Data Index: 768355 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9125. Min Act: -0.1700

Data Index: 896515 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9237. Min Act: -0.1700

Data Index: 896715 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9406. Min Act: -0.1700

Data Index: 932334 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9518. Min Act: -0.1700

Data Index: 1040310 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9382. Min Act: -0.1700

Data Index: 1052580 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9482. Min Act: -0.1700

Data Index: 599394 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9398. Min Act: -0.1700

Data Index: 702433 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9225. Min Act: -0.1700

Data Index: 1616900 (Python Code)

Max Activating Token Index: 429