Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 896 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.9570. Min Act: -0.1700

Data Index: 286532 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.9273. Min Act: -0.1700

Data Index: 138435 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.9083. Min Act: -0.1700

Data Index: 564844 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.8953. Min Act: -0.1700

Data Index: 350601 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.9133. Min Act: -0.1700

Data Index: 812843 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.9260. Min Act: -0.1700

Data Index: 337031 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.9169. Min Act: -0.1700

Data Index: 62177 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.8757. Min Act: -0.1700

Data Index: 61982 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.8716. Min Act: -0.1700

Data Index: 1007311 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.8640. Min Act: -0.1700

Data Index: 469449 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.8458. Min Act: -0.1700

Data Index: 519313 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.8304. Min Act: -0.1700

Data Index: 1235456 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.8252. Min Act: -0.1700

Data Index: 1176091 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.8200. Min Act: -0.1700

Data Index: 347330 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.8087. Min Act: -0.1700

Data Index: 791518 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.8057. Min Act: -0.1700

Data Index: 282551 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.8025. Min Act: -0.1700

Data Index: 723637 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.7965. Min Act: -0.1700

Data Index: 320410 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.7948. Min Act: -0.1700

Data Index: 1146442 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 3.9570. Min Range: -3.9570

Max Act: 3.7718. Min Act: -0.1700

Data Index: 713293 (C4 (Web Text))

Max Activating Token Index: 654