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

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

Neuron 347 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: 3.0525. Min Range: -3.0525

Max Act: 3.0525. Min Act: -0.1700

Data Index: 384870 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 3.0525. Min Range: -3.0525

Max Act: 3.0367. Min Act: -0.1700

Data Index: 855133 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 3.0525. Min Range: -3.0525

Max Act: 3.0367. Min Act: -0.1700

Data Index: 1126810 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 3.0525. Min Range: -3.0525

Max Act: 3.0209. Min Act: -0.1700

Data Index: 311760 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 3.0525. Min Range: -3.0525

Max Act: 3.0051. Min Act: -0.1700

Data Index: 548947 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9893. Min Act: -0.1700

Data Index: 1102277 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9735. Min Act: -0.1700

Data Index: 217750 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9735. Min Act: -0.1700

Data Index: 573956 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9893. Min Act: -0.1700

Data Index: 109177 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9576. Min Act: -0.1700

Data Index: 679433 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9735. Min Act: -0.1700

Data Index: 1204305 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9418. Min Act: -0.1700

Data Index: 204996 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9576. Min Act: -0.1700

Data Index: 118116 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9418. Min Act: -0.1700

Data Index: 1261244 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9576. Min Act: -0.1700

Data Index: 13229 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9260. Min Act: -0.1700

Data Index: 790015 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9101. Min Act: -0.1700

Data Index: 542443 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9260. Min Act: -0.1700

Data Index: 640127 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9260. Min Act: -0.1700

Data Index: 793946 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9101. Min Act: -0.1700

Data Index: 852296 (C4 (Web Text))

Max Activating Token Index: 537