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

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

Neuron 2029 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: 7.0947. Min Range: -7.0947

Max Act: 7.0947. Min Act: -0.1700

Data Index: 495573 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.9697. Min Act: -0.1700

Data Index: 237001 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.6572. Min Act: -0.1700

Data Index: 396271 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.5322. Min Act: -0.1700

Data Index: 505239 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.5010. Min Act: -0.1700

Data Index: 1122763 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.5322. Min Act: -0.1700

Data Index: 249440 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.4697. Min Act: -0.1700

Data Index: 678671 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.4697. Min Act: -0.1700

Data Index: 583778 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.4697. Min Act: -0.1700

Data Index: 22864 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.4385. Min Act: -0.1700

Data Index: 117000 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.4385. Min Act: -0.1700

Data Index: 503408 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.3447. Min Act: -0.1700

Data Index: 977776 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.4072. Min Act: -0.1700

Data Index: 1286501 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.3135. Min Act: -0.1700

Data Index: 552114 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.3135. Min Act: -0.1700

Data Index: 92919 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.3135. Min Act: -0.1700

Data Index: 490367 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.3447. Min Act: -0.1700

Data Index: 822427 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.3135. Min Act: -0.1700

Data Index: 1127684 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.3135. Min Act: -0.1700

Data Index: 1896 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 7.0947. Min Range: -7.0947

Max Act: 6.3135. Min Act: -0.1700

Data Index: 945798 (C4 (Web Text))

Max Activating Token Index: 818