Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 410 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.0696. Min Range: -4.0696

Max Act: 4.0696. Min Act: -0.1700

Data Index: 1103545 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.8820. Min Act: -0.1700

Data Index: 670871 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.8508. Min Act: -0.1700

Data Index: 135735 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.8508. Min Act: -0.1700

Data Index: 384887 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.8195. Min Act: -0.1700

Data Index: 624496 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.8195. Min Act: -0.1700

Data Index: 502725 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.7882. Min Act: -0.1700

Data Index: 922952 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.8195. Min Act: -0.1700

Data Index: 147178 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.6630. Min Act: -0.1700

Data Index: 814249 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.6943. Min Act: -0.1700

Data Index: 39644 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.7100. Min Act: -0.1700

Data Index: 366245 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.6474. Min Act: -0.1700

Data Index: 152077 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.6630. Min Act: -0.1700

Data Index: 738498 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.6317. Min Act: -0.1700

Data Index: 129135 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.6317. Min Act: -0.1700

Data Index: 1068852 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.5848. Min Act: -0.1699

Data Index: 918874 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.5534. Min Act: -0.1700

Data Index: 1483730 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.5848. Min Act: -0.1700

Data Index: 1317674 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.5848. Min Act: -0.1700

Data Index: 424042 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 4.0696. Min Range: -4.0696

Max Act: 3.5534. Min Act: -0.1693

Data Index: 409890 (C4 (Web Text))

Max Activating Token Index: 1023