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

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

Neuron 18 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.8901. Min Act: -0.1700

Data Index: 178998 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.8275. Min Act: -0.1700

Data Index: 600132 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.8275. Min Act: -0.1700

Data Index: 65415 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.8588. Min Act: -0.1700

Data Index: 292866 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.8275. Min Act: -0.1699

Data Index: 1293702 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.7963. Min Act: -0.1700

Data Index: 1304238 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.7963. Min Act: -0.1700

Data Index: 133720 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.7650. Min Act: -0.1700

Data Index: 794912 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.7337. Min Act: -0.1700

Data Index: 860913 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6868. Min Act: -0.1700

Data Index: 159489 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.7024. Min Act: -0.1693

Data Index: 613550 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6868. Min Act: -0.1700

Data Index: 591476 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6555. Min Act: -0.1699

Data Index: 144564 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6868. Min Act: -0.1700

Data Index: 1297543 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6555. Min Act: -0.1699

Data Index: 1292742 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6398. Min Act: -0.1700

Data Index: 714296 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6555. Min Act: -0.1699

Data Index: 1091088 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6241. Min Act: -0.1699

Data Index: 795874 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6241. Min Act: -0.1700

Data Index: 1242695 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6241. Min Act: -0.1699

Data Index: 545695 (C4 (Web Text))

Max Activating Token Index: 848