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

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

Neuron 1991 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: 5.9589. Min Range: -5.9589

Max Act: 5.9589. Min Act: -0.1700

Data Index: 1138545 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.6777. Min Act: -0.1700

Data Index: 644240 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.6464. Min Act: -0.1700

Data Index: 1342818 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.5527. Min Act: -0.1700

Data Index: 930772 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.4277. Min Act: -0.1700

Data Index: 408107 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.5839. Min Act: -0.1700

Data Index: 1275269 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.5214. Min Act: -0.1700

Data Index: 1241106 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.4902. Min Act: -0.1700

Data Index: 1282515 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.4902. Min Act: -0.1700

Data Index: 547609 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.4277. Min Act: -0.1700

Data Index: 254075 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.4902. Min Act: -0.1700

Data Index: 406089 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.4902. Min Act: -0.1700

Data Index: 1118075 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.4277. Min Act: -0.1700

Data Index: 1137407 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.4902. Min Act: -0.1700

Data Index: 907869 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.4277. Min Act: -0.1700

Data Index: 855647 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.4277. Min Act: -0.1699

Data Index: 752847 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.3964. Min Act: -0.1700

Data Index: 855112 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.3964. Min Act: -0.1700

Data Index: 24059 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.5214. Min Act: -0.1700

Data Index: 397620 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 5.9589. Min Range: -5.9589

Max Act: 5.4277. Min Act: -0.1700

Data Index: 598178 (C4 (Web Text))

Max Activating Token Index: 849