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

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

Neuron 1984 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.5206. Min Act: -0.1700

Data Index: 740714 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.5049. Min Act: -0.1700

Data Index: 653040 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.5206. Min Act: -0.1700

Data Index: 1201927 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4893. Min Act: -0.1700

Data Index: 308026 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4579. Min Act: -0.1700

Data Index: 996560 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4109. Min Act: -0.1700

Data Index: 580984 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4422. Min Act: -0.1700

Data Index: 163252 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4422. Min Act: -0.1700

Data Index: 940226 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4579. Min Act: -0.1700

Data Index: 1136324 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4422. Min Act: -0.1700

Data Index: 818881 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4422. Min Act: -0.1700

Data Index: 505255 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4109. Min Act: -0.1700

Data Index: 883397 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4266. Min Act: -0.1700

Data Index: 908155 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.3952. Min Act: -0.1700

Data Index: 610619 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4109. Min Act: -0.1700

Data Index: 170439 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4266. Min Act: -0.1700

Data Index: 702361 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.3952. Min Act: -0.1700

Data Index: 7453 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4266. Min Act: -0.1700

Data Index: 864177 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4109. Min Act: -0.1700

Data Index: 155011 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 3.5206. Min Range: -3.5206

Max Act: 3.4109. Min Act: -0.1700

Data Index: 99462 (C4 (Web Text))

Max Activating Token Index: 229