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

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

Neuron 813 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: 4.5583. Min Range: -4.5583

Max Act: 4.5583. Min Act: -0.1699

Data Index: 757963 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.4958. Min Act: -0.1700

Data Index: 24330 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.4958. Min Act: -0.1700

Data Index: 1288773 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.5271. Min Act: -0.1700

Data Index: 920645 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.4646. Min Act: -0.1700

Data Index: 1286715 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.4958. Min Act: -0.1700

Data Index: 1285127 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.4333. Min Act: -0.1700

Data Index: 749188 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.3708. Min Act: -0.1699

Data Index: 1120801 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.3708. Min Act: -0.1700

Data Index: 362933 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.3708. Min Act: -0.1700

Data Index: 426838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.3708. Min Act: -0.1700

Data Index: 503751 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.3708. Min Act: -0.1700

Data Index: 167781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.3083. Min Act: -0.1700

Data Index: 1112238 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.3083. Min Act: -0.1700

Data Index: 85132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.2770. Min Act: -0.1700

Data Index: 1088647 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.2770. Min Act: -0.1700

Data Index: 237396 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.2770. Min Act: -0.1700

Data Index: 1067601 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.2770. Min Act: -0.1700

Data Index: 143979 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.3083. Min Act: -0.1700

Data Index: 863465 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.5583. Min Range: -4.5583

Max Act: 4.2770. Min Act: -0.1700

Data Index: 750354 (C4 (Web Text))

Max Activating Token Index: 1023