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

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

Neuron 1168 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.2716. Min Act: -0.1700

Data Index: 195428 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1773. Min Act: -0.1700

Data Index: 149094 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1615. Min Act: -0.1700

Data Index: 861219 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1143. Min Act: -0.1700

Data Index: 1321303 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1143. Min Act: -0.1700

Data Index: 311263 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0827. Min Act: -0.1700

Data Index: 62821 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0827. Min Act: -0.1700

Data Index: 1290301 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0670. Min Act: -0.1700

Data Index: 194861 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0670. Min Act: -0.1700

Data Index: 188982 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0827. Min Act: -0.1700

Data Index: 72354 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0670. Min Act: -0.1700

Data Index: 1190269 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0670. Min Act: -0.1700

Data Index: 568503 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0512. Min Act: -0.1700

Data Index: 954147 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0354. Min Act: -0.1700

Data Index: 1214331 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0354. Min Act: -0.1700

Data Index: 1191977 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0354. Min Act: -0.1700

Data Index: 301849 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0670. Min Act: -0.1700

Data Index: 196626 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0354. Min Act: -0.1700

Data Index: 782934 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0354. Min Act: -0.1700

Data Index: 509412 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.0512. Min Act: -0.1700

Data Index: 436588 (C4 (Web Text))

Max Activating Token Index: 656