Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1705 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4814. Min Range: -5.4814

Max Act: 5.4814. Min Act: -0.1700

Data Index: 770174 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 5.4814. Min Range: -5.4814

Max Act: 5.0439. Min Act: -0.1700

Data Index: 560456 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.8252. Min Act: -0.1700

Data Index: 1020755 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.7002. Min Act: -0.1700

Data Index: 6833 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.7002. Min Act: -0.1700

Data Index: 962609 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.5751. Min Act: -0.1692

Data Index: 351725 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.6064. Min Act: -0.1700

Data Index: 1152394 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.5751. Min Act: -0.1700

Data Index: 252215 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.5439. Min Act: -0.1700

Data Index: 880500 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.5439. Min Act: -0.1700

Data Index: 1309822 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.5439. Min Act: -0.1700

Data Index: 538596 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.5439. Min Act: -0.1700

Data Index: 97304 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.5751. Min Act: -0.1700

Data Index: 442543 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.5439. Min Act: -0.1700

Data Index: 1220560 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.5439. Min Act: -0.1700

Data Index: 613860 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.5126. Min Act: -0.1700

Data Index: 1217884 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.5126. Min Act: -0.1700

Data Index: 1199717 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.4501. Min Act: -0.1700

Data Index: 959944 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.4189. Min Act: -0.1700

Data Index: 676056 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 5.4814. Min Range: -5.4814

Max Act: 4.4189. Min Act: -0.1700

Data Index: 49055 (C4 (Web Text))

Max Activating Token Index: 24