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

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

Neuron 1781 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: 3.6667. Min Range: -3.6667

Max Act: 3.6518. Min Act: -0.1700

Data Index: 460864 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.6490. Min Act: -0.1700

Data Index: 1435698 (Python Code)

Max Activating Token Index: 586

Text #2

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.6667. Min Act: -0.1700

Data Index: 953626 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.6522. Min Act: -0.1700

Data Index: 171270 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.6458. Min Act: -0.1562

Data Index: 845788 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5758. Min Act: -0.1700

Data Index: 939825 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5935. Min Act: -0.1698

Data Index: 1644273 (Python Code)

Max Activating Token Index: 991

Text #7

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5943. Min Act: -0.1700

Data Index: 1040492 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5820. Min Act: -0.1700

Data Index: 619855 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5719. Min Act: -0.1699

Data Index: 1605550 (Python Code)

Max Activating Token Index: 207

Text #10

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5595. Min Act: -0.1700

Data Index: 706369 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5596. Min Act: -0.1700

Data Index: 873608 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5315. Min Act: -0.1700

Data Index: 803070 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5533. Min Act: -0.1699

Data Index: 955018 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5421. Min Act: -0.1698

Data Index: 1468836 (Python Code)

Max Activating Token Index: 758

Text #15

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5225. Min Act: -0.1700

Data Index: 1247810 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5140. Min Act: -0.1700

Data Index: 1107116 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5199. Min Act: -0.1700

Data Index: 227998 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5215. Min Act: -0.1700

Data Index: 297676 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 3.6667. Min Range: -3.6667

Max Act: 3.5246. Min Act: -0.1694

Data Index: 1083366 (C4 (Web Text))

Max Activating Token Index: 952