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

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

Neuron 785 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: 3.6260. Min Range: -3.6260

Max Act: 3.6260. Min Act: -0.1700

Data Index: 1039361 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5947. Min Act: -0.1700

Data Index: 738429 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5947. Min Act: -0.1700

Data Index: 877089 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5947. Min Act: -0.1700

Data Index: 888273 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5007. Min Act: -0.1700

Data Index: 1250733 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5007. Min Act: -0.1700

Data Index: 1139125 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5320. Min Act: -0.1700

Data Index: 277197 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5007. Min Act: -0.1700

Data Index: 908542 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4223. Min Act: -0.1700

Data Index: 1535780 (Python Code)

Max Activating Token Index: 454

Text #9

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4223. Min Act: -0.1700

Data Index: 197988 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.3596. Min Act: -0.1700

Data Index: 31857 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.3439. Min Act: -0.1700

Data Index: 1330326 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.3125. Min Act: -0.1700

Data Index: 894107 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.3125. Min Act: -0.1700

Data Index: 1345786 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.2968. Min Act: -0.1700

Data Index: 103702 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.2811. Min Act: -0.1700

Data Index: 467975 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.3125. Min Act: -0.1700

Data Index: 926969 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.2654. Min Act: -0.1700

Data Index: 256353 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.2811. Min Act: -0.1700

Data Index: 1091204 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.2496. Min Act: -0.1700

Data Index: 746579 (C4 (Web Text))

Max Activating Token Index: 701