Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 541 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.4186. Min Act: -0.1700

Data Index: 332896 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.3561. Min Act: -0.1700

Data Index: 155911 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.2623. Min Act: -0.1700

Data Index: 1330217 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.1998. Min Act: -0.1700

Data Index: 475451 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.2623. Min Act: -0.1700

Data Index: 1179669 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.1686. Min Act: -0.1700

Data Index: 1229303 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.1998. Min Act: -0.1700

Data Index: 759071 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.1686. Min Act: -0.1700

Data Index: 1274727 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.1373. Min Act: -0.1700

Data Index: 285483 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.1373. Min Act: -0.1700

Data Index: 286050 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.1686. Min Act: -0.1700

Data Index: 166986 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.0748. Min Act: -0.1700

Data Index: 1152464 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.0748. Min Act: -0.1700

Data Index: 285318 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.0436. Min Act: -0.1700

Data Index: 31814 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.1061. Min Act: -0.1700

Data Index: 969592 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 5.4186. Min Range: -5.4186

Max Act: 4.9811. Min Act: -0.1700

Data Index: 1239587 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.0123. Min Act: -0.1700

Data Index: 1198739 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.0436. Min Act: -0.1700

Data Index: 143155 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.0436. Min Act: -0.1700

Data Index: 1170823 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 5.4186. Min Range: -5.4186

Max Act: 5.1373. Min Act: -0.1700

Data Index: 579650 (C4 (Web Text))

Max Activating Token Index: 261