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

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

Neuron 290 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.7660. Min Act: -0.1700

Data Index: 989827 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.7347. Min Act: -0.1700

Data Index: 784415 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.7347. Min Act: -0.1700

Data Index: 336021 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.7034. Min Act: -0.1700

Data Index: 676303 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.7034. Min Act: -0.1700

Data Index: 307152 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6721. Min Act: -0.1700

Data Index: 903596 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6721. Min Act: -0.1700

Data Index: 1141873 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.5782. Min Act: -0.1700

Data Index: 541193 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6408. Min Act: -0.1700

Data Index: 927762 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6408. Min Act: -0.1700

Data Index: 1220776 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.5469. Min Act: -0.1700

Data Index: 811677 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.5782. Min Act: -0.1700

Data Index: 361154 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.5782. Min Act: -0.1700

Data Index: 103570 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.5469. Min Act: -0.1700

Data Index: 534526 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6408. Min Act: -0.1700

Data Index: 33569 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.5782. Min Act: -0.1700

Data Index: 149817 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6095. Min Act: -0.1700

Data Index: 537012 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.5155. Min Act: -0.1700

Data Index: 167731 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.5782. Min Act: -0.1700

Data Index: 362803 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.5782. Min Act: -0.1700

Data Index: 225260 (C4 (Web Text))

Max Activating Token Index: 270