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

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

Neuron 1073 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.4670. Min Act: -0.1700

Data Index: 262844 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3729. Min Act: -0.1700

Data Index: 808332 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3886. Min Act: -0.1700

Data Index: 1075017 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3572. Min Act: -0.1700

Data Index: 1284901 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3259. Min Act: -0.1700

Data Index: 818740 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3259. Min Act: -0.1700

Data Index: 460038 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3102. Min Act: -0.1700

Data Index: 928170 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3102. Min Act: -0.1700

Data Index: 282535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2944. Min Act: -0.1700

Data Index: 410232 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2944. Min Act: -0.1700

Data Index: 721723 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2787. Min Act: -0.1700

Data Index: 746646 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2787. Min Act: -0.1700

Data Index: 672661 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2630. Min Act: -0.1700

Data Index: 181137 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2630. Min Act: -0.1700

Data Index: 42190 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2316. Min Act: -0.1700

Data Index: 487391 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2316. Min Act: -0.1700

Data Index: 864329 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2316. Min Act: -0.1700

Data Index: 446540 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2316. Min Act: -0.1700

Data Index: 1259641 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2159. Min Act: -0.1700

Data Index: 1031072 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2001. Min Act: -0.1700

Data Index: 237600 (C4 (Web Text))

Max Activating Token Index: 1023