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

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

Neuron 175 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: 3.0634. Min Range: -3.0634

Max Act: 3.0634. Min Act: -0.1700

Data Index: 1175505 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 3.0634. Min Range: -3.0634

Max Act: 3.0474. Min Act: -0.1700

Data Index: 835651 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 3.0634. Min Range: -3.0634

Max Act: 3.0156. Min Act: -0.1700

Data Index: 489356 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9845. Min Act: -0.1700

Data Index: 1266554 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9526. Min Act: -0.1700

Data Index: 251498 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9490. Min Act: -0.1700

Data Index: 1134087 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9536. Min Act: -0.1699

Data Index: 1123790 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9118. Min Act: -0.1700

Data Index: 515874 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9182. Min Act: -0.1700

Data Index: 898306 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9202. Min Act: -0.1700

Data Index: 325250 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9196. Min Act: -0.1700

Data Index: 956756 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9218. Min Act: -0.1700

Data Index: 1086491 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9187. Min Act: -0.1700

Data Index: 1317616 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9192. Min Act: -0.1700

Data Index: 347116 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9038. Min Act: -0.1700

Data Index: 271178 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.9125. Min Act: -0.1700

Data Index: 279816 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.8819. Min Act: -0.1700

Data Index: 141063 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.8771. Min Act: -0.1700

Data Index: 604704 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.8884. Min Act: -0.1700

Data Index: 463266 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 3.0634. Min Range: -3.0634

Max Act: 2.8874. Min Act: -0.1700

Data Index: 1212120 (C4 (Web Text))

Max Activating Token Index: 835