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

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

Neuron 244 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: 3.4668. Min Range: -3.4668

Max Act: 3.4198. Min Act: -0.1700

Data Index: 339983 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4198. Min Act: -0.1700

Data Index: 773201 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4668. Min Act: -0.1700

Data Index: 1484177 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4512. Min Act: -0.1700

Data Index: 991850 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4512. Min Act: -0.1700

Data Index: 1115065 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4355. Min Act: -0.1700

Data Index: 686194 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4355. Min Act: -0.1700

Data Index: 219065 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4668. Min Act: -0.1700

Data Index: 800749 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4512. Min Act: -0.1700

Data Index: 1259046 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4512. Min Act: -0.1700

Data Index: 741963 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4355. Min Act: -0.1700

Data Index: 310665 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4512. Min Act: -0.1700

Data Index: 873932 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4512. Min Act: -0.1700

Data Index: 110291 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4198. Min Act: -0.1700

Data Index: 555598 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4512. Min Act: -0.1700

Data Index: 416640 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4041. Min Act: -0.1700

Data Index: 76117 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4355. Min Act: -0.1700

Data Index: 404092 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4355. Min Act: -0.1700

Data Index: 529616 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4041. Min Act: -0.1700

Data Index: 86209 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 3.4668. Min Range: -3.4668

Max Act: 3.4198. Min Act: -0.1700

Data Index: 104130 (C4 (Web Text))

Max Activating Token Index: 756