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

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

Neuron 1327 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: 5.1968. Min Range: -5.1968

Max Act: 5.1968. Min Act: -0.1700

Data Index: 325415 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 5.1968. Min Range: -5.1968

Max Act: 5.0093. Min Act: -0.1700

Data Index: 1254220 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 5.1968. Min Range: -5.1968

Max Act: 5.0093. Min Act: -0.1700

Data Index: 1138210 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.9780. Min Act: -0.1700

Data Index: 201776 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 5.1968. Min Range: -5.1968

Max Act: 5.0093. Min Act: -0.1700

Data Index: 1243940 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.9155. Min Act: -0.1700

Data Index: 755616 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.9780. Min Act: -0.1700

Data Index: 1090772 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.9155. Min Act: -0.1700

Data Index: 1331471 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.9155. Min Act: -0.1700

Data Index: 1192227 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.9155. Min Act: -0.1700

Data Index: 285585 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.9155. Min Act: -0.1700

Data Index: 115437 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.9155. Min Act: -0.1700

Data Index: 424449 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.9155. Min Act: -0.1700

Data Index: 1139117 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.9155. Min Act: -0.1700

Data Index: 939438 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.8530. Min Act: -0.1700

Data Index: 1248521 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.8530. Min Act: -0.1700

Data Index: 79954 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.8843. Min Act: -0.1700

Data Index: 80853 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.8530. Min Act: -0.1700

Data Index: 69077 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.8530. Min Act: -0.1700

Data Index: 333866 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 5.1968. Min Range: -5.1968

Max Act: 4.8843. Min Act: -0.1700

Data Index: 3713 (C4 (Web Text))

Max Activating Token Index: 738