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

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

Neuron 528 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: 3.2777. Min Range: -3.2777

Max Act: 3.2777. Min Act: -0.1700

Data Index: 1093334 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.2675. Min Act: -0.1700

Data Index: 1280151 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.2009. Min Act: -0.1700

Data Index: 409471 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1950. Min Act: -0.1700

Data Index: 1080031 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1606. Min Act: -0.1700

Data Index: 497979 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1528. Min Act: -0.1700

Data Index: 1566494 (Python Code)

Max Activating Token Index: 506

Text #6

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1329. Min Act: -0.1700

Data Index: 1152349 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1452. Min Act: -0.1700

Data Index: 1336825 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1424. Min Act: -0.1700

Data Index: 382986 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1361. Min Act: -0.1700

Data Index: 112399 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1471. Min Act: -0.1700

Data Index: 1423613 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1040. Min Act: -0.1700

Data Index: 1637498 (Python Code)

Max Activating Token Index: 384

Text #12

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1167. Min Act: -0.1700

Data Index: 1571454 (Python Code)

Max Activating Token Index: 1021

Text #13

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1038. Min Act: -0.1700

Data Index: 492343 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1163. Min Act: -0.1700

Data Index: 499110 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1083. Min Act: -0.1700

Data Index: 990775 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1019. Min Act: -0.1700

Data Index: 1048202 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.0867. Min Act: -0.1700

Data Index: 991310 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.0922. Min Act: -0.1700

Data Index: 19188 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 3.2777. Min Range: -3.2777

Max Act: 3.1182. Min Act: -0.1700

Data Index: 439300 (C4 (Web Text))

Max Activating Token Index: 662