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

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

Neuron 0 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: 3.2921. Min Range: -3.2921

Max Act: 3.2921. Min Act: -0.1700

Data Index: 1086805 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.1257. Min Act: -0.1700

Data Index: 807189 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.1284. Min Act: -0.1700

Data Index: 517489 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.1100. Min Act: -0.1700

Data Index: 6643 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.1077. Min Act: -0.1700

Data Index: 1161102 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0861. Min Act: -0.1700

Data Index: 637072 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0824. Min Act: -0.1700

Data Index: 611182 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0638. Min Act: -0.1700

Data Index: 1098666 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0394. Min Act: -0.1700

Data Index: 287653 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0432. Min Act: -0.1700

Data Index: 947713 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0472. Min Act: -0.1700

Data Index: 941599 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0235. Min Act: -0.1700

Data Index: 910658 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0203. Min Act: -0.1700

Data Index: 66633 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0160. Min Act: -0.1699

Data Index: 1208996 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 3.2921. Min Range: -3.2921

Max Act: 2.9986. Min Act: -0.1700

Data Index: 1232831 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0301. Min Act: -0.1700

Data Index: 149365 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0014. Min Act: -0.1700

Data Index: 456254 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 3.2921. Min Range: -3.2921

Max Act: 2.9731. Min Act: -0.1699

Data Index: 20988 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 3.2921. Min Range: -3.2921

Max Act: 2.9612. Min Act: -0.1700

Data Index: 225233 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 3.2921. Min Range: -3.2921

Max Act: 2.9576. Min Act: -0.1700

Data Index: 866338 (C4 (Web Text))

Max Activating Token Index: 489