Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 130 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.7689. Min Act: -0.1700

Data Index: 411790 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.8002. Min Act: -0.1700

Data Index: 1153466 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6437. Min Act: -0.1700

Data Index: 1080416 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6750. Min Act: -0.1700

Data Index: 940237 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6437. Min Act: -0.1700

Data Index: 1356596 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6750. Min Act: -0.1700

Data Index: 71681 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5811. Min Act: -0.1700

Data Index: 255295 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5968. Min Act: -0.1700

Data Index: 62887 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5968. Min Act: -0.1700

Data Index: 917959 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5968. Min Act: -0.1700

Data Index: 1323208 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5968. Min Act: -0.1700

Data Index: 426959 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5341. Min Act: -0.1700

Data Index: 279536 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5341. Min Act: -0.1700

Data Index: 207490 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5498. Min Act: -0.1700

Data Index: 1298159 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5811. Min Act: -0.1700

Data Index: 409716 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5028. Min Act: -0.1700

Data Index: 1208468 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5341. Min Act: -0.1700

Data Index: 605761 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5655. Min Act: -0.1700

Data Index: 586122 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5655. Min Act: -0.1700

Data Index: 469126 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5341. Min Act: -0.1700

Data Index: 1308014 (C4 (Web Text))

Max Activating Token Index: 355