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

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

Neuron 264 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: 3.2834. Min Range: -3.2834

Max Act: 3.2834. Min Act: -0.1700

Data Index: 283036 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.2048. Min Act: -0.1700

Data Index: 846061 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1261. Min Act: -0.1700

Data Index: 390851 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1103. Min Act: -0.1700

Data Index: 453442 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.0946. Min Act: -0.1700

Data Index: 12381 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.0946. Min Act: -0.1700

Data Index: 466570 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1103. Min Act: -0.1700

Data Index: 1172830 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1103. Min Act: -0.1700

Data Index: 1057316 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.0156. Min Act: -0.1700

Data Index: 879470 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1103. Min Act: -0.1700

Data Index: 877930 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.0472. Min Act: -0.1700

Data Index: 1037433 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 3.2834. Min Range: -3.2834

Max Act: 2.9840. Min Act: -0.1700

Data Index: 506203 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.0314. Min Act: -0.1700

Data Index: 501154 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.0314. Min Act: -0.1700

Data Index: 115083 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.0314. Min Act: -0.1700

Data Index: 586304 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.0156. Min Act: -0.1700

Data Index: 239948 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.0314. Min Act: -0.1700

Data Index: 135529 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 3.2834. Min Range: -3.2834

Max Act: 2.9998. Min Act: -0.1700

Data Index: 717774 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 3.2834. Min Range: -3.2834

Max Act: 2.9840. Min Act: -0.1700

Data Index: 944138 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 3.2834. Min Range: -3.2834

Max Act: 2.9365. Min Act: -0.1700

Data Index: 974799 (C4 (Web Text))

Max Activating Token Index: 888