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

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

Neuron 1557 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: 3.7921. Min Range: -3.7921

Max Act: 3.7921. Min Act: -0.1700

Data Index: 24956 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.7229. Min Act: -0.1700

Data Index: 1168884 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.6673. Min Act: -0.1700

Data Index: 803725 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.6645. Min Act: -0.1700

Data Index: 194529 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.6131. Min Act: -0.1700

Data Index: 296782 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5815. Min Act: -0.1700

Data Index: 270338 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5462. Min Act: -0.1700

Data Index: 1033859 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5633. Min Act: -0.1700

Data Index: 849326 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5657. Min Act: -0.1700

Data Index: 835823 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5280. Min Act: -0.1700

Data Index: 1314780 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5320. Min Act: -0.1700

Data Index: 149259 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5381. Min Act: -0.1700

Data Index: 108742 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5472. Min Act: -0.1700

Data Index: 581227 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5198. Min Act: -0.1700

Data Index: 72566 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5025. Min Act: -0.1700

Data Index: 598251 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5131. Min Act: -0.1700

Data Index: 822478 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.4968. Min Act: -0.1700

Data Index: 865786 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.5271. Min Act: -0.1700

Data Index: 520332 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.4640. Min Act: -0.1700

Data Index: 1545510 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 3.7921. Min Range: -3.7921

Max Act: 3.4364. Min Act: -0.1700

Data Index: 491785 (C4 (Web Text))

Max Activating Token Index: 629