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

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

Neuron 1074 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.9031. Min Act: -0.1700

Data Index: 835153 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.8718. Min Act: -0.1700

Data Index: 405221 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.8718. Min Act: -0.1700

Data Index: 489004 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.8406. Min Act: -0.1700

Data Index: 1123812 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.8093. Min Act: -0.1700

Data Index: 822623 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.8093. Min Act: -0.1700

Data Index: 857987 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.7780. Min Act: -0.1700

Data Index: 180154 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.7467. Min Act: -0.1700

Data Index: 509344 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.7467. Min Act: -0.1700

Data Index: 758980 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.7467. Min Act: -0.1700

Data Index: 964952 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.7154. Min Act: -0.1700

Data Index: 1305055 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.6841. Min Act: -0.1700

Data Index: 1306022 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.6841. Min Act: -0.1700

Data Index: 834235 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.7154. Min Act: -0.1700

Data Index: 1161770 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.6841. Min Act: -0.1700

Data Index: 250043 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.6528. Min Act: -0.1700

Data Index: 733955 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.6372. Min Act: -0.1700

Data Index: 289156 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.6528. Min Act: -0.1700

Data Index: 179288 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.6372. Min Act: -0.1700

Data Index: 915183 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 3.9031. Min Range: -3.9031

Max Act: 3.6528. Min Act: -0.1700

Data Index: 57033 (C4 (Web Text))

Max Activating Token Index: 703