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

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

Neuron 1946 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.2904. Min Act: -0.1700

Data Index: 970942 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.2591. Min Act: -0.1692

Data Index: 470306 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.2279. Min Act: -0.1700

Data Index: 990386 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.2279. Min Act: -0.1700

Data Index: 996004 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.1966. Min Act: -0.1700

Data Index: 1197774 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.1654. Min Act: -0.1700

Data Index: 875078 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0716. Min Act: -0.1700

Data Index: 570494 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0716. Min Act: -0.1700

Data Index: 391599 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0716. Min Act: -0.1700

Data Index: 51237 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0716. Min Act: -0.1700

Data Index: 137182 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0403. Min Act: -0.1700

Data Index: 48748 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0403. Min Act: -0.1700

Data Index: 521668 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 5.2904. Min Range: -5.2904

Max Act: 4.9778. Min Act: -0.1700

Data Index: 1341627 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0403. Min Act: -0.1700

Data Index: 1251659 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0091. Min Act: -0.1700

Data Index: 974985 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0403. Min Act: -0.1700

Data Index: 284506 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0091. Min Act: -0.1700

Data Index: 772415 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0091. Min Act: -0.1700

Data Index: 334116 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 5.2904. Min Range: -5.2904

Max Act: 5.0091. Min Act: -0.1700

Data Index: 305651 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 5.2904. Min Range: -5.2904

Max Act: 4.9310. Min Act: -0.1700

Data Index: 476800 (C4 (Web Text))

Max Activating Token Index: 586