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

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

Neuron 1983 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.9321. Min Act: -0.1700

Data Index: 1177387 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.9008. Min Act: -0.1700

Data Index: 418622 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.8070. Min Act: -0.1700

Data Index: 494541 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.8070. Min Act: -0.1700

Data Index: 1263594 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.8226. Min Act: -0.1700

Data Index: 814180 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7444. Min Act: -0.1700

Data Index: 1155499 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7601. Min Act: -0.1700

Data Index: 221071 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7601. Min Act: -0.1700

Data Index: 253422 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7601. Min Act: -0.1700

Data Index: 1072364 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7757. Min Act: -0.1700

Data Index: 501103 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7288. Min Act: -0.1700

Data Index: 604593 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7444. Min Act: -0.1700

Data Index: 670795 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6975. Min Act: -0.1700

Data Index: 221041 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7131. Min Act: -0.1700

Data Index: 139997 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7288. Min Act: -0.1700

Data Index: 28958 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6505. Min Act: -0.1700

Data Index: 709643 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6662. Min Act: -0.1700

Data Index: 1012004 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6818. Min Act: -0.1700

Data Index: 1176043 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6662. Min Act: -0.1700

Data Index: 1286362 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6818. Min Act: -0.1700

Data Index: 453348 (C4 (Web Text))

Max Activating Token Index: 151