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

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

Neuron 735 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1159. Min Range: -3.1159

Max Act: 3.1159. Min Act: -0.1700

Data Index: 1648335 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 3.1159. Min Range: -3.1159

Max Act: 3.0843. Min Act: -0.1700

Data Index: 1357667 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 3.1159. Min Range: -3.1159

Max Act: 3.0686. Min Act: -0.1700

Data Index: 975545 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 3.1159. Min Range: -3.1159

Max Act: 3.0528. Min Act: -0.1700

Data Index: 422190 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 3.1159. Min Range: -3.1159

Max Act: 3.0212. Min Act: -0.1700

Data Index: 943517 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 3.1159. Min Range: -3.1159

Max Act: 3.0212. Min Act: -0.1700

Data Index: 822618 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 3.1159. Min Range: -3.1159

Max Act: 3.0054. Min Act: -0.1700

Data Index: 528768 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9579. Min Act: -0.1700

Data Index: 273618 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9738. Min Act: -0.1700

Data Index: 896373 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9579. Min Act: -0.1700

Data Index: 1538942 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9579. Min Act: -0.1700

Data Index: 1469773 (Python Code)

Max Activating Token Index: 646

Text #11

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9421. Min Act: -0.1700

Data Index: 928834 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9421. Min Act: -0.1700

Data Index: 379394 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9421. Min Act: -0.1700

Data Index: 425729 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9421. Min Act: -0.1700

Data Index: 501764 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9421. Min Act: -0.1700

Data Index: 447022 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9104. Min Act: -0.1700

Data Index: 68810 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9262. Min Act: -0.1700

Data Index: 739546 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9262. Min Act: -0.1700

Data Index: 1015513 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9104. Min Act: -0.1700

Data Index: 982203 (C4 (Web Text))

Max Activating Token Index: 109