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

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

Neuron 1965 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: 5.3787. Min Range: -5.3787

Max Act: 5.3787. Min Act: -0.1700

Data Index: 1319208 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.2537. Min Act: -0.1700

Data Index: 418142 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.2849. Min Act: -0.1700

Data Index: 1164312 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.0974. Min Act: -0.1700

Data Index: 384264 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.1287. Min Act: -0.1700

Data Index: 355734 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.1287. Min Act: -0.1700

Data Index: 1305466 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.0662. Min Act: -0.1700

Data Index: 1142135 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.0349. Min Act: -0.1700

Data Index: 425419 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.0349. Min Act: -0.1700

Data Index: 725325 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.0037. Min Act: -0.1700

Data Index: 138021 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.0037. Min Act: -0.1700

Data Index: 292538 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.0037. Min Act: -0.1700

Data Index: 454815 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 5.3787. Min Range: -5.3787

Max Act: 4.9724. Min Act: -0.1700

Data Index: 1347348 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.0037. Min Act: -0.1700

Data Index: 667528 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 5.3787. Min Range: -5.3787

Max Act: 4.9412. Min Act: -0.1700

Data Index: 42099 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 5.3787. Min Range: -5.3787

Max Act: 5.0037. Min Act: -0.1700

Data Index: 481503 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 5.3787. Min Range: -5.3787

Max Act: 4.9099. Min Act: -0.1700

Data Index: 226699 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 5.3787. Min Range: -5.3787

Max Act: 4.9099. Min Act: -0.1700

Data Index: 951631 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 5.3787. Min Range: -5.3787

Max Act: 4.9412. Min Act: -0.1700

Data Index: 616235 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 5.3787. Min Range: -5.3787

Max Act: 4.8787. Min Act: -0.1700

Data Index: 214576 (C4 (Web Text))

Max Activating Token Index: 586