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

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

Neuron 1794 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: 5.0926. Min Range: -5.0926

Max Act: 5.0926. Min Act: -0.1290

Data Index: 1516765 (Python Code)

Max Activating Token Index: 959

Text #1

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.7144. Min Act: -0.1700

Data Index: 1515730 (Python Code)

Max Activating Token Index: 617

Text #2

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.6949. Min Act: -0.0973

Data Index: 1448706 (Python Code)

Max Activating Token Index: 330

Text #3

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.5495. Min Act: -0.1698

Data Index: 1461337 (Python Code)

Max Activating Token Index: 944

Text #4

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.5556. Min Act: -0.1684

Data Index: 1598088 (Python Code)

Max Activating Token Index: 107

Text #5

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.5076. Min Act: -0.1700

Data Index: 1478330 (Python Code)

Max Activating Token Index: 391

Text #6

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.4604. Min Act: -0.1700

Data Index: 1360954 (Python Code)

Max Activating Token Index: 784

Text #7

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.4223. Min Act: -0.1700

Data Index: 1631910 (Python Code)

Max Activating Token Index: 775

Text #8

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.3603. Min Act: -0.1699

Data Index: 1421498 (Python Code)

Max Activating Token Index: 599

Text #9

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.3769. Min Act: -0.1699

Data Index: 1536586 (Python Code)

Max Activating Token Index: 449

Text #10

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.3263. Min Act: -0.1699

Data Index: 1544277 (Python Code)

Max Activating Token Index: 40

Text #11

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.3136. Min Act: -0.1671

Data Index: 1483243 (Python Code)

Max Activating Token Index: 325

Text #12

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.3118. Min Act: -0.1700

Data Index: 1522433 (Python Code)

Max Activating Token Index: 782

Text #13

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.2998. Min Act: -0.1693

Data Index: 1512294 (Python Code)

Max Activating Token Index: 1002

Text #14

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.2763. Min Act: -0.0731

Data Index: 1458292 (Python Code)

Max Activating Token Index: 878

Text #15

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.2979. Min Act: -0.1700

Data Index: 1419866 (Python Code)

Max Activating Token Index: 475

Text #16

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.3090. Min Act: -0.1675

Data Index: 1614005 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.2596. Min Act: -0.1700

Data Index: 1618915 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.2932. Min Act: -0.1272

Data Index: 1517352 (Python Code)

Max Activating Token Index: 972

Text #19

Max Range: 5.0926. Min Range: -5.0926

Max Act: 4.2164. Min Act: -0.1371

Data Index: 1553438 (Python Code)

Max Activating Token Index: 707