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

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

Neuron 1128 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: 3.4845. Min Range: -3.4845

Max Act: 3.4845. Min Act: -0.1700

Data Index: 320823 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.4062. Min Act: -0.1700

Data Index: 342265 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.4218. Min Act: -0.1700

Data Index: 1340306 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.4062. Min Act: -0.1700

Data Index: 736258 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3905. Min Act: -0.1700

Data Index: 458601 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.4062. Min Act: -0.1700

Data Index: 1337743 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.4218. Min Act: -0.1700

Data Index: 837834 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3748. Min Act: -0.1700

Data Index: 1038572 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3748. Min Act: -0.1700

Data Index: 91584 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3591. Min Act: -0.1700

Data Index: 900039 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3748. Min Act: -0.1700

Data Index: 882004 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3591. Min Act: -0.1700

Data Index: 700943 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3591. Min Act: -0.1700

Data Index: 952016 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3591. Min Act: -0.1700

Data Index: 762883 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3434. Min Act: -0.1700

Data Index: 1008616 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3591. Min Act: -0.1700

Data Index: 791243 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3748. Min Act: -0.1700

Data Index: 144418 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3277. Min Act: -0.1700

Data Index: 584799 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3434. Min Act: -0.1700

Data Index: 264404 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 3.4845. Min Range: -3.4845

Max Act: 3.3434. Min Act: -0.1700

Data Index: 818041 (C4 (Web Text))

Max Activating Token Index: 543