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

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

Neuron 1023 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: 7.0328. Min Range: -7.0328

Max Act: 7.0328. Min Act: -0.1700

Data Index: 1425608 (Python Code)

Max Activating Token Index: 602

Text #1

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.9056. Min Act: -0.1700

Data Index: 521404 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.9074. Min Act: -0.1700

Data Index: 637511 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8431. Min Act: -0.1700

Data Index: 1511672 (Python Code)

Max Activating Token Index: 154

Text #4

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8970. Min Act: -0.1699

Data Index: 1568561 (Python Code)

Max Activating Token Index: 690

Text #5

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8730. Min Act: -0.1700

Data Index: 1564840 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8923. Min Act: -0.1700

Data Index: 395971 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8439. Min Act: -0.1700

Data Index: 1305375 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8446. Min Act: -0.1700

Data Index: 773077 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8246. Min Act: -0.1700

Data Index: 747205 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8413. Min Act: -0.1700

Data Index: 1515797 (Python Code)

Max Activating Token Index: 558

Text #11

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.7981. Min Act: -0.1700

Data Index: 997691 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8146. Min Act: -0.1700

Data Index: 122378 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.7931. Min Act: -0.1700

Data Index: 337440 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.7987. Min Act: -0.1700

Data Index: 1301859 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8125. Min Act: -0.1700

Data Index: 1428768 (Python Code)

Max Activating Token Index: 649

Text #16

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.7666. Min Act: -0.1700

Data Index: 1456895 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8053. Min Act: -0.1700

Data Index: 1539980 (Python Code)

Max Activating Token Index: 344

Text #18

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.7898. Min Act: -0.1700

Data Index: 197079 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 7.0328. Min Range: -7.0328

Max Act: 6.8125. Min Act: -0.1700

Data Index: 495255 (C4 (Web Text))

Max Activating Token Index: 364