Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 956 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.3703. Min Act: -0.1700

Data Index: 453963 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.3546. Min Act: -0.1700

Data Index: 341445 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.3546. Min Act: -0.1700

Data Index: 1531127 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.3389. Min Act: -0.1700

Data Index: 1389412 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.3232. Min Act: -0.1700

Data Index: 1013218 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.3075. Min Act: -0.1700

Data Index: 199590 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.3232. Min Act: -0.1700

Data Index: 1253925 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.3075. Min Act: -0.1700

Data Index: 23121 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2918. Min Act: -0.1700

Data Index: 652465 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2761. Min Act: -0.1700

Data Index: 1446823 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2761. Min Act: -0.1700

Data Index: 572802 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2918. Min Act: -0.1700

Data Index: 860055 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2604. Min Act: -0.1700

Data Index: 759491 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2761. Min Act: -0.1700

Data Index: 1192095 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2604. Min Act: -0.1700

Data Index: 353141 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2604. Min Act: -0.1700

Data Index: 49441 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2604. Min Act: -0.1700

Data Index: 348076 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2604. Min Act: -0.1700

Data Index: 485400 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2447. Min Act: -0.1700

Data Index: 995161 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2447. Min Act: -0.1700

Data Index: 1155665 (C4 (Web Text))

Max Activating Token Index: 170