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

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

Neuron 1618 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: 3.6081. Min Range: -3.6081

Max Act: 3.6081. Min Act: -0.1689

Data Index: 798509 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.4620. Min Act: -0.1699

Data Index: 1207056 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3939. Min Act: -0.1435

Data Index: 779078 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3888. Min Act: -0.1473

Data Index: 1535561 (Python Code)

Max Activating Token Index: 743

Text #4

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3778. Min Act: -0.1700

Data Index: 315929 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3858. Min Act: -0.1435

Data Index: 495390 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3144. Min Act: -0.1700

Data Index: 149394 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3190. Min Act: -0.1700

Data Index: 1362964 (Python Code)

Max Activating Token Index: 118

Text #8

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2635. Min Act: -0.1699

Data Index: 1434999 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2639. Min Act: -0.1676

Data Index: 1649755 (Python Code)

Max Activating Token Index: 610

Text #10

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2697. Min Act: -0.1700

Data Index: 483675 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2616. Min Act: -0.1699

Data Index: 1259136 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2802. Min Act: -0.1699

Data Index: 1144823 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2638. Min Act: -0.1503

Data Index: 396921 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2711. Min Act: -0.1700

Data Index: 306371 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2506. Min Act: -0.1700

Data Index: 1093175 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2201. Min Act: -0.1700

Data Index: 290243 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2167. Min Act: -0.1700

Data Index: 660551 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2039. Min Act: -0.1689

Data Index: 336104 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2001. Min Act: -0.1505

Data Index: 904185 (C4 (Web Text))

Max Activating Token Index: 480