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

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

Neuron 1360 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.8005. Min Act: -0.1700

Data Index: 1348923 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.6441. Min Act: -0.1700

Data Index: 188603 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.6441. Min Act: -0.1700

Data Index: 586996 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.6441. Min Act: -0.1700

Data Index: 1141638 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.6128. Min Act: -0.1700

Data Index: 108216 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5815. Min Act: -0.1700

Data Index: 1231899 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5815. Min Act: -0.1700

Data Index: 1028983 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5501. Min Act: -0.1700

Data Index: 1331382 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5501. Min Act: -0.1700

Data Index: 642240 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5188. Min Act: -0.1700

Data Index: 638584 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.4875. Min Act: -0.1700

Data Index: 609069 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5501. Min Act: -0.1700

Data Index: 756782 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5188. Min Act: -0.1700

Data Index: 761569 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.4875. Min Act: -0.1700

Data Index: 254992 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5188. Min Act: -0.1700

Data Index: 853834 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.4875. Min Act: -0.1700

Data Index: 327080 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.5188. Min Act: -0.1700

Data Index: 1081020 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.4875. Min Act: -0.1700

Data Index: 538044 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.4561. Min Act: -0.1700

Data Index: 698212 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 3.8005. Min Range: -3.8005

Max Act: 3.4875. Min Act: -0.1700

Data Index: 668445 (C4 (Web Text))

Max Activating Token Index: 468