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

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

Neuron 104 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: 3.0642. Min Range: -3.0642

Max Act: 3.0642. Min Act: -0.1700

Data Index: 286487 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.0642. Min Range: -3.0642

Max Act: 3.0169. Min Act: -0.1700

Data Index: 1097738 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.0642. Min Range: -3.0642

Max Act: 3.0010. Min Act: -0.1700

Data Index: 862965 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.9536. Min Act: -0.1700

Data Index: 633094 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.9536. Min Act: -0.1700

Data Index: 1096592 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8425. Min Act: -0.1700

Data Index: 1219679 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8107. Min Act: -0.1700

Data Index: 1214275 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.7948. Min Act: -0.1700

Data Index: 766432 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.7470. Min Act: -0.1700

Data Index: 926916 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.7629. Min Act: -0.1700

Data Index: 840385 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.6990. Min Act: -0.1700

Data Index: 1284491 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.7150. Min Act: -0.1700

Data Index: 1350013 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.7310. Min Act: -0.1700

Data Index: 325758 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.7150. Min Act: -0.1700

Data Index: 1323802 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.6830. Min Act: -0.1700

Data Index: 1216670 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.6990. Min Act: -0.1700

Data Index: 1118110 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.6990. Min Act: -0.1700

Data Index: 880588 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.6830. Min Act: -0.1700

Data Index: 578573 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.6830. Min Act: -0.1700

Data Index: 647726 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.6670. Min Act: -0.1700

Data Index: 816448 (C4 (Web Text))

Max Activating Token Index: 1023