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

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

Neuron 285 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: 3.7301. Min Range: -3.7301

Max Act: 3.7301. Min Act: -0.1700

Data Index: 150436 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.6049. Min Act: -0.1700

Data Index: 314457 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.5422. Min Act: -0.1700

Data Index: 94042 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.5109. Min Act: -0.1700

Data Index: 142303 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.5109. Min Act: -0.1700

Data Index: 354489 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.4796. Min Act: -0.1700

Data Index: 85688 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.3855. Min Act: -0.1700

Data Index: 48756 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.3541. Min Act: -0.1700

Data Index: 1289032 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.3855. Min Act: -0.1700

Data Index: 1099443 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.3541. Min Act: -0.1700

Data Index: 1060126 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.3227. Min Act: -0.1700

Data Index: 1648246 (Python Code)

Max Activating Token Index: 403

Text #11

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.3227. Min Act: -0.1700

Data Index: 898549 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.3227. Min Act: -0.1700

Data Index: 1109754 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.3227. Min Act: -0.1700

Data Index: 84447 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.2913. Min Act: -0.1700

Data Index: 999281 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.2913. Min Act: -0.1700

Data Index: 392102 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.2913. Min Act: -0.1700

Data Index: 987608 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.2913. Min Act: -0.1700

Data Index: 199199 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.2599. Min Act: -0.1700

Data Index: 1099653 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 3.7301. Min Range: -3.7301

Max Act: 3.2599. Min Act: -0.1700

Data Index: 196430 (C4 (Web Text))

Max Activating Token Index: 230