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

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

Neuron 363 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.5685. Min Act: -0.1700

Data Index: 616492 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.4748. Min Act: -0.1700

Data Index: 245880 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.3810. Min Act: -0.1700

Data Index: 263375 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.3185. Min Act: -0.1700

Data Index: 60570 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.2560. Min Act: -0.1700

Data Index: 291911 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.1623. Min Act: -0.1700

Data Index: 537910 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.1310. Min Act: -0.1700

Data Index: 868242 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.1623. Min Act: -0.1700

Data Index: 422322 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.0998. Min Act: -0.1700

Data Index: 1310298 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.0373. Min Act: -0.1700

Data Index: 893120 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.0060. Min Act: -0.1700

Data Index: 460262 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 5.5685. Min Range: -5.5685

Max Act: 4.9123. Min Act: -0.1700

Data Index: 565413 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 5.5685. Min Range: -5.5685

Max Act: 4.9435. Min Act: -0.1700

Data Index: 823575 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 5.5685. Min Range: -5.5685

Max Act: 4.9748. Min Act: -0.1700

Data Index: 68886 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 5.5685. Min Range: -5.5685

Max Act: 4.9435. Min Act: -0.1700

Data Index: 1195954 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 5.5685. Min Range: -5.5685

Max Act: 4.9748. Min Act: -0.1700

Data Index: 857920 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 5.5685. Min Range: -5.5685

Max Act: 4.9435. Min Act: -0.1700

Data Index: 1122148 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 5.5685. Min Range: -5.5685

Max Act: 4.9435. Min Act: -0.1700

Data Index: 1088844 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 5.5685. Min Range: -5.5685

Max Act: 4.9123. Min Act: -0.1700

Data Index: 711127 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 5.5685. Min Range: -5.5685

Max Act: 4.8810. Min Act: -0.1700

Data Index: 210612 (C4 (Web Text))

Max Activating Token Index: 690