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

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

Neuron 1155 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.7706. Min Act: -0.1700

Data Index: 839386 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.6456. Min Act: -0.1700

Data Index: 24558 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.6143. Min Act: -0.1700

Data Index: 784549 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.5831. Min Act: -0.1700

Data Index: 502142 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.5206. Min Act: -0.1700

Data Index: 603318 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.4893. Min Act: -0.1700

Data Index: 103800 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.4893. Min Act: -0.1700

Data Index: 364018 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.4581. Min Act: -0.1700

Data Index: 179168 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.4893. Min Act: -0.1700

Data Index: 1101863 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.3956. Min Act: -0.1700

Data Index: 1121952 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.3956. Min Act: -0.1700

Data Index: 684723 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.3956. Min Act: -0.1700

Data Index: 925723 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.3331. Min Act: -0.1700

Data Index: 1081722 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.3643. Min Act: -0.1700

Data Index: 451087 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.3956. Min Act: -0.1700

Data Index: 485108 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.3956. Min Act: -0.1700

Data Index: 1315832 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.3643. Min Act: -0.1700

Data Index: 25049 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.3331. Min Act: -0.1700

Data Index: 7911 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.3018. Min Act: -0.1700

Data Index: 1303153 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 5.7706. Min Range: -5.7706

Max Act: 5.3331. Min Act: -0.1700

Data Index: 1656472 (Python Code)

Max Activating Token Index: 405