Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 709 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.9511. Min Act: -0.1700

Data Index: 360849 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.8573. Min Act: -0.1700

Data Index: 1077038 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.7636. Min Act: -0.1700

Data Index: 123026 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.6698. Min Act: -0.1700

Data Index: 450138 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.6386. Min Act: -0.1700

Data Index: 639080 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.6073. Min Act: -0.1699

Data Index: 787318 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.6073. Min Act: -0.1697

Data Index: 165197 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.6073. Min Act: -0.1700

Data Index: 719243 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.5448. Min Act: -0.1700

Data Index: 1163581 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.5448. Min Act: -0.1700

Data Index: 1205277 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.5761. Min Act: -0.1699

Data Index: 99242 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.5136. Min Act: -0.1699

Data Index: 1135356 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.4823. Min Act: -0.1700

Data Index: 714626 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.5448. Min Act: -0.1700

Data Index: 1122259 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.4823. Min Act: -0.1700

Data Index: 1245311 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.4823. Min Act: -0.1700

Data Index: 681132 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.5448. Min Act: -0.1700

Data Index: 193677 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.5136. Min Act: -0.1700

Data Index: 645651 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.5136. Min Act: -0.1700

Data Index: 869078 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 5.9511. Min Range: -5.9511

Max Act: 5.4823. Min Act: -0.1700

Data Index: 820625 (C4 (Web Text))

Max Activating Token Index: 518