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

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

Neuron 1922 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: 5.4124. Min Range: -5.4124

Max Act: 5.4124. Min Act: -0.1700

Data Index: 324670 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.4124. Min Act: -0.1700

Data Index: 550636 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3812. Min Act: -0.1700

Data Index: 849072 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3499. Min Act: -0.1700

Data Index: 106147 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3499. Min Act: -0.1700

Data Index: 589093 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3187. Min Act: -0.1700

Data Index: 1142643 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3187. Min Act: -0.1700

Data Index: 167583 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3187. Min Act: -0.1700

Data Index: 1105810 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3187. Min Act: -0.1700

Data Index: 336359 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2874. Min Act: -0.1700

Data Index: 1170823 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2874. Min Act: -0.1700

Data Index: 215936 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2874. Min Act: -0.1700

Data Index: 908057 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2874. Min Act: -0.1700

Data Index: 890287 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2874. Min Act: -0.1700

Data Index: 1198056 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2562. Min Act: -0.1700

Data Index: 835041 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2249. Min Act: -0.1700

Data Index: 692415 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2562. Min Act: -0.1700

Data Index: 1064082 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2874. Min Act: -0.1700

Data Index: 1167116 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2249. Min Act: -0.1700

Data Index: 24722 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.1937. Min Act: -0.1700

Data Index: 956627 (C4 (Web Text))

Max Activating Token Index: 803