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

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

Neuron 671 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: 5.2505. Min Range: -5.2505

Max Act: 5.2505. Min Act: -0.1700

Data Index: 797085 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 5.2505. Min Range: -5.2505

Max Act: 5.1255. Min Act: -0.1700

Data Index: 462430 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 5.2505. Min Range: -5.2505

Max Act: 5.0943. Min Act: -0.1700

Data Index: 92221 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 5.2505. Min Range: -5.2505

Max Act: 5.0943. Min Act: -0.1700

Data Index: 857336 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 5.2505. Min Range: -5.2505

Max Act: 5.0005. Min Act: -0.1700

Data Index: 1274156 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.9693. Min Act: -0.1700

Data Index: 189307 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 5.2505. Min Range: -5.2505

Max Act: 5.0005. Min Act: -0.1700

Data Index: 493050 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.9068. Min Act: -0.1700

Data Index: 261688 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.9068. Min Act: -0.1700

Data Index: 896725 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.9380. Min Act: -0.1700

Data Index: 347724 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.9693. Min Act: -0.1700

Data Index: 1190658 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.9068. Min Act: -0.1699

Data Index: 1014896 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.9068. Min Act: -0.1700

Data Index: 79375 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.8130. Min Act: -0.1700

Data Index: 710815 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.9068. Min Act: -0.1700

Data Index: 224677 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.8755. Min Act: -0.1700

Data Index: 141803 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.8755. Min Act: -0.1700

Data Index: 1115480 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.8755. Min Act: -0.1700

Data Index: 870065 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.8755. Min Act: -0.1700

Data Index: 1109885 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 5.2505. Min Range: -5.2505

Max Act: 4.8755. Min Act: -0.1700

Data Index: 666752 (C4 (Web Text))

Max Activating Token Index: 805