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

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

Neuron 1425 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1951. Min Range: -3.1951

Max Act: 3.1951. Min Act: -0.1700

Data Index: 1243506 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 3.1951. Min Range: -3.1951

Max Act: 3.1006. Min Act: -0.1700

Data Index: 1136411 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 3.1951. Min Range: -3.1951

Max Act: 3.0217. Min Act: -0.1700

Data Index: 1264098 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 3.1951. Min Range: -3.1951

Max Act: 3.0059. Min Act: -0.1700

Data Index: 436366 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9426. Min Act: -0.1700

Data Index: 1325228 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9426. Min Act: -0.1700

Data Index: 654947 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9426. Min Act: -0.1700

Data Index: 753793 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9267. Min Act: -0.1700

Data Index: 405985 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9267. Min Act: -0.1700

Data Index: 827130 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9109. Min Act: -0.1700

Data Index: 465713 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9267. Min Act: -0.1700

Data Index: 442048 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9267. Min Act: -0.1700

Data Index: 545964 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.8950. Min Act: -0.1700

Data Index: 464609 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.8791. Min Act: -0.1700

Data Index: 765809 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9109. Min Act: -0.1700

Data Index: 402870 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.8791. Min Act: -0.1700

Data Index: 619306 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.8633. Min Act: -0.1700

Data Index: 1029567 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.8791. Min Act: -0.1700

Data Index: 962989 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.8791. Min Act: -0.1700

Data Index: 230215 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.8791. Min Act: -0.1700

Data Index: 922681 (C4 (Web Text))

Max Activating Token Index: 813