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

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

Neuron 59 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.1650. Min Range: -4.1650

Max Act: 4.1650. Min Act: -0.1700

Data Index: 1106646 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 4.1650. Min Range: -4.1650

Max Act: 4.0400. Min Act: -0.1700

Data Index: 613348 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 4.1650. Min Range: -4.1650

Max Act: 4.0087. Min Act: -0.1700

Data Index: 77624 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.9462. Min Act: -0.1700

Data Index: 324471 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.9775. Min Act: -0.1700

Data Index: 663806 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.9775. Min Act: -0.1700

Data Index: 510151 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.9775. Min Act: -0.1700

Data Index: 1245910 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.9775. Min Act: -0.1700

Data Index: 1210229 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.9462. Min Act: -0.1700

Data Index: 810985 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.8836. Min Act: -0.1700

Data Index: 799697 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.9149. Min Act: -0.1700

Data Index: 374200 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.9149. Min Act: -0.1700

Data Index: 204210 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.8836. Min Act: -0.1700

Data Index: 614530 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.9149. Min Act: -0.1700

Data Index: 944900 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.8836. Min Act: -0.1700

Data Index: 1002604 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.8524. Min Act: -0.1700

Data Index: 64147 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.8524. Min Act: -0.1700

Data Index: 1173210 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.8836. Min Act: -0.1700

Data Index: 641647 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.8524. Min Act: -0.1700

Data Index: 119581 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 4.1650. Min Range: -4.1650

Max Act: 3.8211. Min Act: -0.1700

Data Index: 501619 (C4 (Web Text))

Max Activating Token Index: 632