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

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

Neuron 1067 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: 3.6406. Min Range: -3.6406

Max Act: 3.6257. Min Act: -0.1693

Data Index: 609940 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.6406. Min Act: -0.1700

Data Index: 1473414 (Python Code)

Max Activating Token Index: 808

Text #2

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.5645. Min Act: -0.1619

Data Index: 37814 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.5118. Min Act: -0.1700

Data Index: 1479977 (Python Code)

Max Activating Token Index: 975

Text #4

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.4945. Min Act: -0.1690

Data Index: 231384 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.4495. Min Act: -0.1670

Data Index: 792023 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.4593. Min Act: -0.1619

Data Index: 340568 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.4442. Min Act: -0.1683

Data Index: 120713 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.4323. Min Act: -0.1692

Data Index: 468867 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.4159. Min Act: -0.1619

Data Index: 33947 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.4323. Min Act: -0.1699

Data Index: 347992 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.4265. Min Act: -0.1619

Data Index: 1507730 (Python Code)

Max Activating Token Index: 893

Text #12

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.3907. Min Act: -0.1693

Data Index: 1378008 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.4070. Min Act: -0.1699

Data Index: 875968 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.3373. Min Act: -0.1654

Data Index: 1222938 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.3636. Min Act: -0.1700

Data Index: 824668 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.3584. Min Act: -0.1697

Data Index: 996257 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.3578. Min Act: -0.1619

Data Index: 1410930 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.3638. Min Act: -0.1694

Data Index: 513567 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.3685. Min Act: -0.1646

Data Index: 1065183 (C4 (Web Text))

Max Activating Token Index: 599