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

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

Neuron 593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0994. Min Range: -5.0994

Max Act: 5.0994. Min Act: -0.1700

Data Index: 546460 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.9744. Min Act: -0.1700

Data Index: 982713 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.9744. Min Act: -0.1700

Data Index: 880888 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.9119. Min Act: -0.1700

Data Index: 907290 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.8494. Min Act: -0.1700

Data Index: 1241044 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.8181. Min Act: -0.1700

Data Index: 702650 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.7556. Min Act: -0.1700

Data Index: 631208 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.7244. Min Act: -0.1700

Data Index: 952972 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.7244. Min Act: -0.1700

Data Index: 1347164 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.7556. Min Act: -0.1700

Data Index: 321556 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.6619. Min Act: -0.1700

Data Index: 1064953 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.7556. Min Act: -0.1700

Data Index: 65769 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.7244. Min Act: -0.1700

Data Index: 190541 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.7244. Min Act: -0.1700

Data Index: 1269115 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.7244. Min Act: -0.1700

Data Index: 589080 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.7244. Min Act: -0.1700

Data Index: 227477 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.7244. Min Act: -0.1700

Data Index: 455310 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.6931. Min Act: -0.1700

Data Index: 1016351 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.6619. Min Act: -0.1700

Data Index: 884087 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.6931. Min Act: -0.1700

Data Index: 596930 (C4 (Web Text))

Max Activating Token Index: 879