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

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

Neuron 242 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: 5.5662. Min Range: -5.5662

Max Act: 5.5662. Min Act: -0.1700

Data Index: 870713 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.5662. Min Act: -0.1700

Data Index: 871477 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.4724. Min Act: -0.1700

Data Index: 847446 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.4724. Min Act: -0.1700

Data Index: 648635 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.4724. Min Act: -0.1700

Data Index: 244309 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.4724. Min Act: -0.1700

Data Index: 638244 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.4412. Min Act: -0.1700

Data Index: 812112 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.4412. Min Act: -0.1700

Data Index: 1135746 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.4412. Min Act: -0.1700

Data Index: 1260467 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.4099. Min Act: -0.1699

Data Index: 1195781 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.4099. Min Act: -0.1700

Data Index: 789384 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.3474. Min Act: -0.1700

Data Index: 930221 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.3787. Min Act: -0.1700

Data Index: 765549 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.4099. Min Act: -0.1700

Data Index: 693128 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.4412. Min Act: -0.1700

Data Index: 1107387 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.3162. Min Act: -0.1700

Data Index: 180270 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.2849. Min Act: -0.1700

Data Index: 997024 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.2849. Min Act: -0.1700

Data Index: 341176 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.3162. Min Act: -0.1699

Data Index: 156804 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 5.5662. Min Range: -5.5662

Max Act: 5.3162. Min Act: -0.1700

Data Index: 132811 (C4 (Web Text))

Max Activating Token Index: 510